thread_process_action
import math
import random
import re
import sys
import threading
from time import ctime, sleep
from lxml import etree
import pprint
import requests
from selenium import webdriver f = open('spider_北上广深_district.txt', 'r', encoding='utf-8')
f.closed
POOL_URL_DISTRICT_LIST = []
for i in f:
d = i.replace('\n', '').replace(' ', '').split('"')
for ii in d:
if ii.find('http') > -1:
POOL_URL_DISTRICT_LIST.append(ii) POOL_URL_DISTRICT_MAXPAGE_NUM_DIC = {} res_dic = {} # https://m.lianjia.com/gz/ershoufang/tianhequ/pg23/
# https://m.lianjia.com/sz/ershoufang/longhuaqu/pg23/
# https://m.lianjia.com/bj/ershoufang/haidianqu/pg34/
# 'https://sz.lianjia.com/ershoufang/futianqu/'
# 'https://gz.lianjia.com/ershoufang/panyu/'
# 'https://bj.lianjia.com/ershoufang/miyun/' POOL_URL_DISTRICT_LIST_B = []
MAX_PAGE_NUM = 100 def gen_url(num=MAX_PAGE_NUM):
for url in POOL_URL_DISTRICT_LIST:
l = url.split('//')[1].split('lianjia')
[city, district] = l
city = city[:-1]
district = district.split('.com/')[1]
if city != 'sh':
url_ = '%s%s/%s' % ('https://m.lianjia.com/', city, district)
else:
url_ = '%s%s/' % ('http://m.sh.lianjia.com/', district) POOL_URL_DISTRICT_MAXPAGE_NUM_DIC[url_] = num
POOL_URL_DISTRICT_LIST_B.append(url_) gen_url()
exception_url_list = [] URL_NUM_EACH_THREAD = 100 * 0.6 * 4
res_dic = {} # QPS_TIME_UNIT_B = 2 todo_url_list = []
for url_ in POOL_URL_DISTRICT_LIST_B:
if url_.find('sh.') > -1:
page_addition = 'd'
else:
page_addition = 'pg'
for page_num in range(1, MAX_PAGE_NUM, 1):
url = '%s%s%s/' % (url_, page_addition, page_num)
todo_url_list.append(url) LEN = len(todo_url_list) browser = webdriver.Firefox() def grab_todo_url_list(browser):
global res_dic, todo_url_list d = random.randint(1, 2)
if d % 2 == 0:
todo_url_list.reverse() my_control = len(todo_url_list)
my_control_start = random.randint(0, my_control)
for i in range(my_control_start, my_control, 1):
if len(todo_url_list) > i:
url = todo_url_list[i]
if url not in todo_url_list:
continue
sleep(1)
browser.get(url)
html = browser.page_source
web_site = ''
url_pass_flag = 0
if html.find('price_total') > -1:
selector = etree.HTML(html)
url_l = selector.xpath('//a[@class="a_mask"]/@href')
des_l = selector.xpath('//div[@class="item_other text_cut"]/text()')
price_total_l = selector.xpath('//span[@class="price_total"]/em/text()')
unit_price_l = selector.xpath('//span[@class="unit_price"]/text()')
url_pass_flag = 1
elif html.find('xiaoquname') > -1:
web_site = 'sh'
selector = etree.HTML(html)
url_l = selector.xpath('//ul[@class="fang-list"]/li/a/@href')
xiaoquname_l = selector.xpath('//span[@class="xiaoquname"]/text()')
area_l = selector.xpath('//p[@class="f-area"]/text()')
price_total_l = selector.xpath('//span[@class="f-price"]/text()')
url_pass_flag = 1
# https://m.lianjia.com/bj/ershoufang/yizhuangkaifaqu/pg87
# http://m.sh.lianjia.com/ershoufang/jinshan/d78
elif html.find('搜索条件') > -1 or url.find('/lf/') > -1:
print(111, url)
url_pass_flag = 2
if url_pass_flag == 1:
res_dic[url] = {}
len_l = len(url_l)
res_dic[url]['items_list'] = []
len_l_ = len_l - 1
for i in range(0, len_l_, 1):
d = {}
d['spider_url'] = url
d['item_url'] = url_l[i]
d['des'] = des_l[i] if web_site == '' else '%s||%s' % (
area_l[i].replace('\n', '').replace(',', '').replace(' ', ''),
xiaoquname_l[i].replace(',', '').replace(' ', ''))
d['price_total'] = price_total_l[i]
d['unit_price'] = unit_price_l[i] if web_site == '' else 'sh'
res_dic[url]['items_list'].append(d)
if url_pass_flag != 0:
if url in todo_url_list:
l_index = todo_url_list.index(url)
del todo_url_list[l_index]
else:
if url not in todo_url_list:
todo_url_list.append(url)
browser.close() class MyThread(threading.Thread):
def __init__(self, func, args, name=''):
threading.Thread.__init__(self)
self.name = name
self.func = func
self.args = args def run(self):
self.func(self.args) MAX_EXCEPTION_URL_NUM = 0 def deal_exception_url_list():
global todo_url_list
browser = webdriver.Firefox()
if len(todo_url_list) > MAX_EXCEPTION_URL_NUM:
grab_todo_url_list(browser)
else:
return
deal_exception_url_list() POOL_URL_LEN_B = len(POOL_URL_DISTRICT_LIST_B) def main():
print('starting at:', ctime())
threads_list = []
thread_sum = math.ceil(LEN / URL_NUM_EACH_THREAD)
for nloop in range(0, thread_sum, 1):
browser = webdriver.Firefox()
thread_instance = MyThread(grab_todo_url_list, (browser), grab_todo_url_list.__name__)
threads_list.append(thread_instance)
# 主进程将在所有非守护进程退出后,退出
for t in threads_list:
t.setDaemon = False
t.start()
# wait for all thrades to finish
for t in threads_list:
t.join()
# pprint.pprint(res_dic)
deal_exception_url_list()
print('end_r:', ctime())
f_name = 'mobile_lianjia_ershoufang_BSGS.csv'
f = open(f_name, 'w', encoding='utf-8-sig')
str = 'spider_url,item_url,des,price_total,unit_price\n'
f.write(str)
f.closed
f = open(f_name, 'a', encoding='utf-8-sig') for url in res_dic:
try:
for d in res_dic[url]['items_list']:
str = '%s,%s,%s,%s,%s\n' % (d['spider_url'], d['item_url'], d['des'], d['price_total'], d['unit_price'])
f.write(str)
except Exception:
print(Exception)
f.closed
print('end_w:', ctime()) if __name__ == '__main__':
main()
# -*- coding: UTF-8 -*-
import math
import random
import sys
import threading
from time import ctime, sleep import requests MAX_PAGINATION = 100
pagination = MAX_PAGINATION
QPS = 50
QPS_TIME_UNIT = 1
# http://lbs.amap.com/api/webservice/guide/tools/info
INFOCODE_OK = ''
file_name_key_pool = 'key_pool.pool'
KEY_POOL_LIST = []
touse_key = ''
f = open(file_name_key_pool, 'r', encoding='utf-8')
for i in f:
try:
list_ = i.split('\t')
key = i.split('\t')[1].split()
KEY_POOL_LIST.append(key[0])
except Exception:
print(Exception)
KEY_POOL_NUM_INDICATOR = len(KEY_POOL_LIST) URL_TYPE = 'http://restapi.amap.com/v3/place/text'
touse_key = ''
keywords = '&keywords='
OFFSET = '&offset=2'
CITYLIMIT = '&citylimit=false'
# 060100 购物服务 商场 商场
# 060101 购物服务 商场 购物中心
# 060102 购物服务 商场 普通商场
# 060400 购物服务 超级市场 超市 POI_TYPES = '&types=060100|060101|060102|060400'
URL_FOR_CHANGE_KEY = 'http://restapi.amap.com/v3/place/text?key=%s&types=060100&city=010&OFFSET=1' change_key_qps = 0 def change_key():
global touse_key, change_key_qps
# 高德没有遵守自己的QPS/日限策略;所不能通过其返回码,来控制key的使用;
mean_use_key = random.randint(0, KEY_POOL_NUM_INDICATOR)
for i in range(mean_use_key, KEY_POOL_NUM_INDICATOR, 1):
key = KEY_POOL_LIST[i]
if key == touse_key:
if i == KEY_POOL_NUM_INDICATOR:
change_key()
return
else:
continue
touse_key = key
url = URL_FOR_CHANGE_KEY % (touse_key)
try:
change_key_qps += 1
if change_key_qps % QPS == 0:
sleep(QPS_TIME_UNIT)
r = requests.get(url)
json_ = r.json()
except Exception:
print('requests.get(url)', Exception)
change_key()
return
infocode = json_['infocode']
if not infocode == INFOCODE_OK:
if i == KEY_POOL_NUM_INDICATOR:
sys.exit('NOInvalidKEY')
change_key()
return
return FNAME = '【商场任务】28个城市_任务列表_20170727 - 副本.csv'
tosupply_dic = {}
todo_list = []
fo = open(FNAME, 'r', encoding='gbk')
file_line_num = 0
for i in fo:
file_line_num += 1
if file_line_num == 1:
continue
todo_list.append(file_line_num)
tosupply_dic[file_line_num] = {}
l = i.replace('\n', '').replace(',,,,,,,', '').split(',')
dic_ = {}
dic_['sequence_number'] = l[0]
dic_['type'] = l[1]
dic_['city'] = l[2]
dic_['district'] = l[3]
dic_['address'] = l[4]
dic_['name'] = l[5]
dic_['gd_type_1'], dic_['gd_type_2'], dic_['gd_type_3'], dic_['gd_name'], dic_['gd_province'], dic_['gd_city'], \
dic_['gd_district'], dic_['gd_address'] = ['', '', '', '', '', '', '', '']
tosupply_dic[file_line_num] = dic_
LEN = len(todo_list)
EACH_THREAD_REQUEST_NUM = 30 requests_counter = 0
tosupply_dic_len = len(tosupply_dic)
tosupply_dic_len_ = tosupply_dic_len - 1 def supply_dic(nloop):
global tosupply_dic, requests_counter, todo_list
print(len(todo_list))
d = random.randint(1, 2)
if d % 2 == 0:
todo_list.reverse() for file_line_num in todo_list:
if file_line_num not in todo_list:
continue
t = threading.current_thread()
print('nloop=',nloop)
print(' t._ident=',t._ident)
dic_ = tosupply_dic[file_line_num]
city = dic_['district']
name = dic_['name']
url = '%s?key=%s&keywords=%s&city=%s%s%s%s' % (URL_TYPE, touse_key, name, city, POI_TYPES, OFFSET, CITYLIMIT)
if requests_counter % QPS == 0:
sleep(QPS_TIME_UNIT)
try:
r = requests.get(url)
r_json = r.json()
except Exception:
if file_line_num not in todo_list:
todo_list.append(file_line_num)
continue
infocode = r_json['infocode']
if infocode == '':
count = r_json['count']
if int(count) > 0:
pois_list = r_json['pois']
pos_dic = pois_list[0]
tosupply_dic[file_line_num]['gd_type_one'] = pos_dic['type']
tosupply_dic[file_line_num]['gd_type_1'], tosupply_dic[file_line_num]['gd_type_2'], \
tosupply_dic[file_line_num]['gd_type_3'] = pos_dic['type'].split('|')[0].split(';')
tosupply_dic[file_line_num]['gd_province'] = pos_dic['pname']
tosupply_dic[file_line_num]['gd_city'] = pos_dic['cityname']
tosupply_dic[file_line_num]['gd_district'] = pos_dic['adname']
tosupply_dic[file_line_num]['gd_address'] = pos_dic['address']
elif int(count) == 0:
tosupply_dic[file_line_num]['gd_name'] = 'GD-NO-DATA'
if file_line_num in todo_list:
list_index = todo_list.index(file_line_num)
del todo_list[list_index]
print(file_line_num)
else:
if file_line_num not in todo_list:
todo_list.append(file_line_num)
change_key() MAX_EXCEPTION_URL_NUM = 0 def deal_exception_list():
global todo_list
print(todo_list)
if len(todo_list) > MAX_EXCEPTION_URL_NUM:
supply_dic()
else:
return
deal_exception_list() class MyThread(threading.Thread):
def __init__(self, func, args, name=''):
threading.Thread.__init__(self)
self.name = name
self.func = func
self.args = args def run(self):
self.func(self.args) def main():
print('starting at:', ctime())
threads_list = []
thread_sum = math.ceil(tosupply_dic_len / EACH_THREAD_REQUEST_NUM)
print(185, thread_sum)
for nloop in range(0, thread_sum, 1):
thread_instance = MyThread(supply_dic,(nloop),supply_dic.__name__)
threads_list.append(thread_instance)
# 主进程将在所有非守护进程退出后,退出
for t in threads_list:
t.setDaemon = False
t.start()
# wait for all thrades to finish
for t in threads_list:
t.join()
deal_exception_list() FGEN = 'GEN_28.csv'
fo = open(FGEN, 'w', encoding='utf-8-sig')
fo.write(
'序号,类别编号,城市名称,区域 地址,商圈名,gd_type_one,gd_type_1,gd_type_2,gd_type_3,gd_name,gd_province,gd_city,gd_district,gd_address\n')
fo.closed
fo = open(FGEN, 'a', encoding='utf-8-sig')
for file_line_num in tosupply_dic:
if file_line_num == 1:
continue
dic_ = tosupply_dic[file_line_num]
str = '%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s\n' % (
dic_['sequence_number'], dic_['type'], dic_['city'], dic_['district'], dic_['address'],
dic_['name'], dic_['gd_type_one'], dic_['gd_type_1'], dic_['gd_type_2'], dic_['gd_type_3'], dic_['gd_name'],
dic_['gd_province'],
dic_['gd_city'],
dic_['gd_district'],
dic_['gd_address'])
fo.write(str)
fo.closed if __name__ == '__main__':
main()
16G内存OK 4G内存 --- no
# -*- coding: UTF-8 -*-
import math
import random
import sys
import threading
from time import ctime, sleep import requests # fo = open('电影院任务列表_20170724_新增列 - 副本 (12).csv', 'r', encoding='utf-8')
# file_line_num = 0
# for i in fo:
# if file_line_num == 0:
# continue
# l = i.replace('\n','').split(',')
#
# ddd = 5
# MAX_OFFSET = 25
# OFFSET = MAX_OFFSET - 1
MAX_PAGINATION = 100
pagination = MAX_PAGINATION
QPS = 50
QPS_TIME_UNIT = 1
# http://lbs.amap.com/api/webservice/guide/tools/info
INFOCODE_OK = ''
file_name_key_pool = 'key_pool.pool'
KEY_POOL_LIST = []
touse_key = ''
f = open(file_name_key_pool, 'r', encoding='utf-8')
for i in f:
try:
list_ = i.split('\t')
key = i.split('\t')[1].split()
KEY_POOL_LIST.append(key[0])
except Exception:
print(Exception)
KEY_POOL_NUM_INDICATOR = len(KEY_POOL_LIST) # http://restapi.amap.com/v3/place/text?key=&keywords=奥斯卡漯河店&types=080601&city=漯河&offset=1
# http://restapi.amap.com/v3/place/text?key=&keywords=奥斯卡漯河店&types=080601&city=漯河&offset=2
# 2得到的结果更接近期望值
URL_TYPE = 'http://restapi.amap.com/v3/place/text'
touse_key = ''
keywords = '&keywords='
OFFSET = '&offset=2'
## 己方数据 city-name 不匹配 citylimit true-->false
# 华中区 湖北 钟祥 电影院 横店荆门店 横店影视股份有限公司 0 GD-NO-DATA
CITYLIMIT = '&citylimit=false'
# 080601 体育休闲服务 影剧院 电影院
POI_TYPES = '&types=080601'
URL_FOR_CHANGE_KEY = 'http://restapi.amap.com/v3/place/text?key=%s&types=060100&city=010&OFFSET=1' change_key_qps = 0 def change_key():
global touse_key, change_key_qps
# 高德没有遵守自己的QPS/日限策略;所不能通过其返回码,来控制key的使用;
mean_use_key = random.randint(0, KEY_POOL_NUM_INDICATOR)
for i in range(mean_use_key, KEY_POOL_NUM_INDICATOR, 1):
key = KEY_POOL_LIST[i]
if key == touse_key:
if i == KEY_POOL_NUM_INDICATOR:
change_key()
return
else:
continue
touse_key = key
url = URL_FOR_CHANGE_KEY % (touse_key)
try:
change_key_qps += 1
if change_key_qps % QPS == 0:
sleep(QPS_TIME_UNIT)
r = requests.get(url)
json_ = r.json()
except Exception:
print('requests.get(url)', Exception)
change_key()
return
infocode = json_['infocode']
if not infocode == INFOCODE_OK:
if i == KEY_POOL_NUM_INDICATOR:
sys.exit('NOInvalidKEY')
change_key()
return
return FNAME = '电影院任务列表_20170724.csv'
tosupply_dic = {}
fo = open(FNAME, 'r', encoding='gbk')
file_line_num = 0
for i in fo:
file_line_num += 1
if file_line_num == 1:
continue
tosupply_dic[file_line_num] = {}
is_from_past_line = 1 if len(i.split(',,,,,,,,')) > 1 else 0
l = i.replace('\n', '').replace(',,,,,,,', '').split(',')
dic_ = {}
dic_['sequence_number'] = l[0]
dic_['area'] = l[1] if is_from_past_line == 0 else tosupply_dic[file_line_num - 1]['area']
dic_['province'] = l[2] if is_from_past_line == 0 else tosupply_dic[file_line_num - 1][
'province']
dic_['city'] = l[3] if is_from_past_line == 0 else tosupply_dic[file_line_num - 1]['city']
dic_['district'] = ''
dic_['address'] = ''
dic_['buliding'] = ''
dic_['longitude_latitude'] = ''
dic_['busniess_type'] = l[8] if is_from_past_line == 0 else l[1]
dic_['name'] = l[9] if is_from_past_line == 0 else l[2]
dic_['parent_company'] = l[10] if is_from_past_line == 0 else tosupply_dic[file_line_num - 1]['parent_company']
dic_['is_from_past_line'] = is_from_past_line
dic_['gd_name'] = ''
dic_['gd_city'] = ''
tosupply_dic[file_line_num] = dic_ EACH_THREAD_REQUEST_NUM = 30
exception_line_num_list = [] # keywords = '&keywords='
# OFFSET = '&offset=1'
# CITYLIMIT = '&citylimit=true'
# # 080601 体育休闲服务 影剧院 电影院
# POI_TYPES = '&types=080601'
#
# http://restapi.amap.com/v3/place/text?key=&keywords=重庆万盛DAV国际影城&city=重庆&types=080601&offset=1&citylimit=true
requests_counter = 0
tosupply_dic_len = len(tosupply_dic)
tosupply_dic_len_ = tosupply_dic_len - 1 # thread_strat_file_line_num
def supply_dic(thread_strat_file_line_num):
global tosupply_dic, requests_counter, tosupply_dic_len_, exception_line_num_list
for loop in range(0, EACH_THREAD_REQUEST_NUM, 1):
file_line_num = thread_strat_file_line_num + loop
if file_line_num - 2 > tosupply_dic_len_:
return
if file_line_num < 2 or len(tosupply_dic[file_line_num]['district']) > 0:
if file_line_num in exception_line_num_list:
list_index = exception_line_num_list.index(file_line_num)
del exception_line_num_list[list_index]
continue
dic_ = tosupply_dic[file_line_num]
city = dic_['city']
name = dic_['name']
url = '%s?key=%s&keywords=%s&city=%s%s%s%s' % (URL_TYPE, touse_key, name, city, POI_TYPES, OFFSET, CITYLIMIT)
if requests_counter % QPS == 0:
sleep(QPS_TIME_UNIT)
try:
r = requests.get(url)
r_json = r.json()
except Exception:
if file_line_num not in exception_line_num_list:
exception_line_num_list.append(file_line_num)
continue
infocode = r_json['infocode']
if infocode == '':
count = r_json['count']
if int(count) > 0:
pois_list = r_json['pois']
pos_dic = pois_list[0]
tosupply_dic[file_line_num]['district'] = pos_dic['adname'] if len(pos_dic['address']) <= 2:
print(pos_dic)
print(pos_dic['address'])
tosupply_dic[file_line_num]['address'] = pos_dic['address'] if len(pos_dic['address']) > 2 else '高德缺地址'
if len(pos_dic['address']) <= 2:
print(tosupply_dic[file_line_num]['address'])
tosupply_dic[file_line_num]['longitude_latitude'] = pos_dic['location']
tosupply_dic[file_line_num]['gd_name'] = pos_dic['name']
tosupply_dic[file_line_num]['gd_city'] = pos_dic['cityname'] elif int(count) == 0:
tosupply_dic[file_line_num]['gd_name'] = 'GD-NO-DATA'
if file_line_num in exception_line_num_list:
list_index = exception_line_num_list.index(file_line_num)
del exception_line_num_list[list_index]
else:
if file_line_num not in exception_line_num_list:
exception_line_num_list.append(file_line_num)
change_key() MAX_EXCEPTION_URL_NUM = 0 def deal_exception_list():
global exception_line_num_list
print(exception_line_num_list)
if len(exception_line_num_list) > MAX_EXCEPTION_URL_NUM:
for thread_strat_file_line_num in exception_line_num_list:
supply_dic(thread_strat_file_line_num)
else:
return
deal_exception_list() class MyThread(threading.Thread):
def __init__(self, func, args, name=''):
threading.Thread.__init__(self)
self.name = name
self.func = func
self.args = args def run(self):
self.func(self.args) # 通灌北路58号苏宁广场7层701
# 林源路创基尚城B区3层
# 民治书香门第上河坊2栋2层
# 东欣大道东欣广场城市综合体E01四楼
# 横栏镇茂辉工业区乐丰四路21号永耀商业广场B幢之四(永耀人才市场旁)
# 信江路西侧金峰城市广场1栋5层502(鹏泰购物广场5楼、迪欧咖啡楼上)
# 上陡门学院中路人才大厦一层(东瓯影城)
# 丰庆路710号(世纪联华超市4楼)
# 风度中路13号百老汇商业城5层(美特斯邦威楼上)
# 龙阳路2000号(龙阳广场5层)
# 容城大道东12号(容城天骄写字楼3层)
# 解放大道387号(汉口宗关水厂)南国西汇城市广场二期5层
# 后沙峪镇安泰大街9号院(中粮祥云小镇)7号楼2层
# 华强新天地3楼华时代美食城门口(横店电影院门口)
# 南三环西路16号1号楼首地大峡谷购物中心5层
# 永兴路7号院1号楼龙湖北京大兴天街购物中心L3层Z2
def gen_building(str):
start_ = 0
end_ = len(str)
res = ''
start_flag = 0
end_flag = 0
if str.find('号') > -1:
start_ = str.find('号') + 1
start_flag = 1
elif str.find('交汇处') > -1:
start_ = str.find('交汇处') + 1 + 2
start_flag = 1
elif str.find('交叉口') > -1:
start_ = str.find('交叉口') + 1 + 2
start_flag = 1
elif str.find('路') > -1:
start_ = str.find('路') + 1
start_flag = 1
elif str.find('道') > -1:
start_ = str.find('道') + 1
start_flag = 1 if str.find('层') > -1:
end_ = str.find('层') + 1
end_flag = 1
elif str.find('楼') > -1:
end_ = str.find('楼') + 1
end_flag = 1
if start_flag == 1 or end_flag == 1:
res = ''.join((list(str)[start_:end_]))
if res.find('(') > -1 or res.find('(') > -1:
# new rule
res = res.replace('(', '').replace(')', '').replace('(', '').replace(')', '')
return res def main():
print('starting at:', ctime())
threads_list = []
thread_sum = math.ceil(tosupply_dic_len / EACH_THREAD_REQUEST_NUM)
print(185, thread_sum)
for nloop in range(0, thread_sum, 1):
thread_strat_file_line_num = nloop * EACH_THREAD_REQUEST_NUM
print(thread_strat_file_line_num)
thread_instance = MyThread(supply_dic, (thread_strat_file_line_num), supply_dic.__name__)
threads_list.append(thread_instance)
# 主进程将在所有非守护进程退出后,退出
for t in threads_list:
t.setDaemon = False
t.start()
# wait for all thrades to finish
for t in threads_list:
t.join()
# pprint.pprint(res_dic) deal_exception_list()
for i in exception_line_num_list:
print('EXCEPTION', i)
FGEN = '电影院任务列表_20170724_新增列_已计算楼宇.csv'
fo = open(FGEN, 'w', encoding='utf-8-sig')
fo.write('序号,地理区域,省份,城市,区域,地址,所属楼宇,经纬度,商圈属性,店铺名,所属院线,is_from_past_line,gd_name,gd_city\n')
fo.closed
fo = open(FGEN, 'a', encoding='utf-8-sig')
for file_line_num in tosupply_dic:
if file_line_num == 1:
continue
dic_ = tosupply_dic[file_line_num]
str = '%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s\n' % (
dic_['sequence_number'], dic_['area'], dic_['province'], dic_['city'], dic_['district'],
dic_['address'].replace(',', ' '),
gen_building(dic_['address']), dic_['longitude_latitude'].replace(',', ' '), dic_['busniess_type'],
dic_['name'],
dic_['parent_company'],
dic_['is_from_past_line'], dic_['gd_name'], dic_['gd_city'])
fo.write(str)
fo.closed if __name__ == '__main__':
main()
# -*- coding: UTF-8 -*-
import math
import random
import sys
import threading
from time import ctime, sleep import requests # fo = open('电影院任务列表_20170724_新增列 - 副本 (12).csv', 'r', encoding='utf-8')
# file_line_num = 0
# for i in fo:
# if file_line_num == 0:
# continue
# l = i.replace('\n','').split(',')
#
# ddd = 5
# MAX_OFFSET = 25
# OFFSET = MAX_OFFSET - 1
MAX_PAGINATION = 100
pagination = MAX_PAGINATION
QPS = 50
QPS_TIME_UNIT = 1
# http://lbs.amap.com/api/webservice/guide/tools/info
INFOCODE_OK = '10000'
file_name_key_pool = 'key_pool.pool'
KEY_POOL_LIST = []
touse_key = ''
f = open(file_name_key_pool, 'r', encoding='utf-8')
for i in f:
try:
list_ = i.split('\t')
key = i.split('\t')[1].split()
KEY_POOL_LIST.append(key[0])
except Exception:
print(Exception)
KEY_POOL_NUM_INDICATOR = len(KEY_POOL_LIST) # http://restapi.amap.com/v3/place/text?key=&keywords=奥斯卡漯河店&types=080601&city=漯河&offset=1
# http://restapi.amap.com/v3/place/text?key=&keywords=奥斯卡漯河店&types=080601&city=漯河&offset=2
# 2得到的结果更接近期望值
URL_TYPE = 'http://restapi.amap.com/v3/place/text'
touse_key = ''
keywords = '&keywords='
OFFSET = '&offset=2'
## 己方数据 city-name 不匹配 citylimit true-->false
# 华中区 湖北 钟祥 电影院 横店荆门店 横店影视股份有限公司 0 GD-NO-DATA
CITYLIMIT = '&citylimit=false'
# 080601 体育休闲服务 影剧院 电影院
POI_TYPES = '&types=080601'
URL_FOR_CHANGE_KEY = 'http://restapi.amap.com/v3/place/text?key=%s&types=060100&city=010&OFFSET=1' change_key_qps = 0 def change_key():
global touse_key, change_key_qps
# 高德没有遵守自己的QPS/日限策略;所不能通过其返回码,来控制key的使用;
mean_use_key = random.randint(0, KEY_POOL_NUM_INDICATOR)
for i in range(mean_use_key, KEY_POOL_NUM_INDICATOR, 1):
key = KEY_POOL_LIST[i]
if key == touse_key:
if i == KEY_POOL_NUM_INDICATOR:
change_key()
return
else:
continue
touse_key = key
url = URL_FOR_CHANGE_KEY % (touse_key)
try:
change_key_qps += 1
if change_key_qps % QPS == 0:
sleep(QPS_TIME_UNIT)
r = requests.get(url)
json_ = r.json()
except Exception:
print('requests.get(url)', Exception)
change_key()
return
infocode = json_['infocode']
if not infocode == INFOCODE_OK:
if i == KEY_POOL_NUM_INDICATOR:
sys.exit('NOInvalidKEY')
change_key()
return
return FNAME = '电影院任务列表_20170724.csv'
tosupply_dic = {}
fo = open(FNAME, 'r', encoding='gbk')
file_line_num = 0
for i in fo:
file_line_num += 1
if file_line_num == 1:
continue
tosupply_dic[file_line_num] = {}
is_from_past_line = 1 if len(i.split(',,,,,,,,')) > 1 else 0
l = i.replace('\n', '').replace(',,,,,,,', '').split(',')
dic_ = {}
dic_['sequence_number'] = l[0]
dic_['area'] = l[1] if is_from_past_line == 0 else tosupply_dic[file_line_num - 1]['area']
dic_['province'] = l[2] if is_from_past_line == 0 else tosupply_dic[file_line_num - 1][
'province']
dic_['city'] = l[3] if is_from_past_line == 0 else tosupply_dic[file_line_num - 1]['city']
dic_['district'] = ''
dic_['address'] = ''
dic_['buliding'] = ''
dic_['longitude_latitude'] = ''
dic_['busniess_type'] = l[8] if is_from_past_line == 0 else l[1]
dic_['name'] = l[9] if is_from_past_line == 0 else l[2]
dic_['parent_company'] = l[10] if is_from_past_line == 0 else tosupply_dic[file_line_num - 1]['parent_company']
dic_['is_from_past_line'] = is_from_past_line
dic_['gd_name'] = ''
dic_['gd_city'] = ''
tosupply_dic[file_line_num] = dic_ EACH_THREAD_REQUEST_NUM = 30
exception_line_num_list = [] # keywords = '&keywords='
# OFFSET = '&offset=1'
# CITYLIMIT = '&citylimit=true'
# # 080601 体育休闲服务 影剧院 电影院
# POI_TYPES = '&types=080601'
#
# http://restapi.amap.com/v3/place/text?key=&keywords=重庆万盛DAV国际影城&city=重庆&types=080601&offset=1&citylimit=true
requests_counter = 0
tosupply_dic_len = len(tosupply_dic)
tosupply_dic_len_ = tosupply_dic_len - 1 # thread_strat_file_line_num
def supply_dic(thread_strat_file_line_num):
global tosupply_dic, requests_counter, tosupply_dic_len_, exception_line_num_list
for loop in range(0, EACH_THREAD_REQUEST_NUM, 1):
file_line_num = thread_strat_file_line_num + loop
if file_line_num - 2 > tosupply_dic_len_:
return
if file_line_num < 2 or len(tosupply_dic[file_line_num]['district']) > 0:
if file_line_num in exception_line_num_list:
list_index = exception_line_num_list.index(file_line_num)
del exception_line_num_list[list_index]
continue
dic_ = tosupply_dic[file_line_num]
city = dic_['city']
name = dic_['name']
url = '%s?key=%s&keywords=%s&city=%s%s%s%s' % (URL_TYPE, touse_key, name, city, POI_TYPES, OFFSET, CITYLIMIT)
if requests_counter % QPS == 0:
sleep(QPS_TIME_UNIT)
try:
r = requests.get(url)
r_json = r.json()
except Exception:
if file_line_num not in exception_line_num_list:
exception_line_num_list.append(file_line_num)
continue
infocode = r_json['infocode']
if infocode == '10000':
count = r_json['count']
if int(count) > 0:
pois_list = r_json['pois']
pos_dic = pois_list[0]
tosupply_dic[file_line_num]['district'] = pos_dic['adname'] if len(pos_dic['address']) <= 2:
print(pos_dic)
print(pos_dic['address'])
tosupply_dic[file_line_num]['address'] = pos_dic['address'] if len(pos_dic['address']) > 2 else '高德缺地址'
if len(pos_dic['address']) <= 2:
print(tosupply_dic[file_line_num]['address'])
tosupply_dic[file_line_num]['longitude_latitude'] = pos_dic['location']
tosupply_dic[file_line_num]['gd_name'] = pos_dic['name']
tosupply_dic[file_line_num]['gd_city'] = pos_dic['cityname'] elif int(count) == 0:
tosupply_dic[file_line_num]['gd_name'] = 'GD-NO-DATA'
if file_line_num in exception_line_num_list:
list_index = exception_line_num_list.index(file_line_num)
del exception_line_num_list[list_index]
else:
if file_line_num not in exception_line_num_list:
exception_line_num_list.append(file_line_num)
change_key() MAX_EXCEPTION_URL_NUM = 0 def deal_exception_list():
global exception_line_num_list
print(exception_line_num_list)
if len(exception_line_num_list) > MAX_EXCEPTION_URL_NUM:
for thread_strat_file_line_num in exception_line_num_list:
supply_dic(thread_strat_file_line_num)
else:
return
deal_exception_list() class MyThread(threading.Thread):
def __init__(self, func, args, name=''):
threading.Thread.__init__(self)
self.name = name
self.func = func
self.args = args def run(self):
self.func(self.args) # 通灌北路58号苏宁广场7层701
# 林源路创基尚城B区3层
# 民治书香门第上河坊2栋2层
# 东欣大道东欣广场城市综合体E01四楼
# 横栏镇茂辉工业区乐丰四路21号永耀商业广场B幢之四(永耀人才市场旁)
# 信江路西侧金峰城市广场1栋5层502(鹏泰购物广场5楼、迪欧咖啡楼上)
# 上陡门学院中路人才大厦一层(东瓯影城)
# 丰庆路710号(世纪联华超市4楼)
# 风度中路13号百老汇商业城5层(美特斯邦威楼上)
# 龙阳路2000号(龙阳广场5层)
# 容城大道东12号(容城天骄写字楼3层)
# 解放大道387号(汉口宗关水厂)南国西汇城市广场二期5层
# 后沙峪镇安泰大街9号院(中粮祥云小镇)7号楼2层
# 华强新天地3楼华时代美食城门口(横店电影院门口)
# 南三环西路16号1号楼首地大峡谷购物中心5层
# 永兴路7号院1号楼龙湖北京大兴天街购物中心L3层Z2
def gen_building(str):
start_ = 0
end_ = len(str)
res = ''
start_flag = 0
end_flag = 0
if str.find('号') > -1:
start_ = str.find('号') + 1
start_flag = 1
elif str.find('交汇处') > -1:
start_ = str.find('交汇处') + 1 + 2
start_flag = 1
elif str.find('交叉口') > -1:
start_ = str.find('交叉口') + 1 + 2
start_flag = 1
elif str.find('路') > -1:
start_ = str.find('路') + 1
start_flag = 1
elif str.find('道') > -1:
start_ = str.find('道') + 1
start_flag = 1 if str.find('层') > -1:
end_ = str.find('层') + 1
end_flag = 1
elif str.find('楼') > -1:
end_ = str.find('楼') + 1
end_flag = 1
if start_flag == 1 or end_flag == 1:
res = ''.join((list(str)[start_:end_]))
if res.find('('):
# new rule
res = res.replace('(', '').replace(')', '')
return res def main():
print('starting at:', ctime())
threads_list = []
thread_sum = math.ceil(tosupply_dic_len / EACH_THREAD_REQUEST_NUM)
print(185, thread_sum)
for nloop in range(0, thread_sum, 1):
thread_strat_file_line_num = nloop * EACH_THREAD_REQUEST_NUM
print(thread_strat_file_line_num)
thread_instance = MyThread(supply_dic, (thread_strat_file_line_num), supply_dic.__name__)
threads_list.append(thread_instance)
# 主进程将在所有非守护进程退出后,退出
for t in threads_list:
t.setDaemon = False
t.start()
# wait for all thrades to finish
for t in threads_list:
t.join()
# pprint.pprint(res_dic) deal_exception_list()
for i in exception_line_num_list:
print('EXCEPTION', i)
FGEN = '电影院任务列表_20170724_新增列_已计算楼宇.csv'
fo = open(FGEN, 'w', encoding='utf-8-sig')
fo.write('序号,地理区域,省份,城市,区域,地址,所属楼宇,经纬度,商圈属性,店铺名,所属院线,is_from_past_line,gd_name,gd_city\n')
fo.closed
fo = open(FGEN, 'a', encoding='utf-8-sig')
for file_line_num in tosupply_dic:
if file_line_num == 1:
continue
dic_ = tosupply_dic[file_line_num]
str = '%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s\n' % (
dic_['sequence_number'], dic_['area'], dic_['province'], dic_['city'], dic_['district'],
dic_['address'].replace(',', ' '),
gen_building(dic_['address']), dic_['longitude_latitude'].replace(',', ' '), dic_['busniess_type'],
dic_['name'],
dic_['parent_company'],
dic_['is_from_past_line'], dic_['gd_name'], dic_['gd_city'])
fo.write(str)
fo.closed if __name__ == '__main__':
main()
高德缺地址
{'id': 'B0FFGJYCPN', 'name': '横店电影城(原阳店)', 'type': '体育休闲服务;影剧院;电影院', 'typecode': '', 'biz_type': 'cinema', 'address': [], 'location': '113.960307,35.065736', 'tel': '0373-5911199', 'distance': [], 'biz_ext': [], 'pname': '河南省', 'cityname': '新乡市', 'adname': '原阳县', 'importance': [], 'shopid': [], 'shopinfo': '', 'poiweight': []}
[]
高德缺地址
{'id': 'B0FFH0368R', 'name': '横店电影城', 'type': '体育休闲服务;影剧院;电影院', 'typecode': '', 'biz_type': 'cinema', 'address': [], 'location': '118.430053,29.862110', 'tel': [], 'distance': [], 'biz_ext': [], 'pname': '安徽省', 'cityname': '黄山市', 'adname': '歙县', 'importance': [], 'shopid': [], 'shopinfo': '', 'poiweight': []}
[]
高德缺地址
[300, 30, 2, 390, 330, 480, 570, 900, 840, 450, 1140, 630, 990, 180, 1050, 90, 240, 360, 720, 750, 690, 1170, 60, 1230, 960, 210, 1200, 930, 510, 150, 600, 870, 1080, 810, 660, 540, 270, 420, 1110, 120, 780, 1020, 1113, 813, 544, 69, 94, 119]
[390, 330, 570, 840, 1140, 990, 1050, 240, 720, 690, 60, 960, 1200, 510, 600, 1080, 660, 270, 1110, 780, 1113]
[330, 840, 990, 240, 690, 960, 510, 1080, 270, 780]
[840, 240, 960, 1080, 780]
[240, 1080]
[1080]
[]
# -*- coding: UTF-8 -*-
import re
import pprint
import json
import time
import math
import sys
import requests
import threading
from time import ctime, sleep
import random # fo = open('电影院任务列表_20170724_新增列 - 副本 (12).csv', 'r', encoding='utf-8')
# file_line_num = 0
# for i in fo:
# if file_line_num == 0:
# continue
# l = i.replace('\n','').split(',')
#
# ddd = 5
# MAX_OFFSET = 25
# OFFSET = MAX_OFFSET - 1
MAX_PAGINATION = 100
pagination = MAX_PAGINATION
QPS = 50
QPS_TIME_UNIT = 1
# http://lbs.amap.com/api/webservice/guide/tools/info
INFOCODE_OK = ''
file_name_key_pool = 'key_pool.pool'
KEY_POOL_LIST = []
touse_key = ''
f = open(file_name_key_pool, 'r', encoding='utf-8')
for i in f:
try:
list_ = i.split('\t')
key = i.split('\t')[1].split()
KEY_POOL_LIST.append(key[0])
except Exception:
print(Exception)
KEY_POOL_NUM_INDICATOR = len(KEY_POOL_LIST) # http://restapi.amap.com/v3/place/text?key=&keywords=奥斯卡漯河店&types=080601&city=漯河&offset=1
# http://restapi.amap.com/v3/place/text?key=&keywords=奥斯卡漯河店&types=080601&city=漯河&offset=2
# 2得到的结果更接近期望值
URL_TYPE = 'http://restapi.amap.com/v3/place/text'
touse_key = ''
keywords = '&keywords='
OFFSET = '&offset=2'
## 己方数据 city-name 不匹配 citylimit true-->false
# 华中区 湖北 钟祥 电影院 横店荆门店 横店影视股份有限公司 0 GD-NO-DATA
CITYLIMIT = '&citylimit=false'
# 080601 体育休闲服务 影剧院 电影院
POI_TYPES = '&types=080601'
URL_FOR_CHANGE_KEY = 'http://restapi.amap.com/v3/place/text?key=%s&types=060100&city=010&OFFSET=1' change_key_qps = 0 def change_key():
global touse_key, change_key_qps
# 高德没有遵守自己的QPS/日限策略;所不能通过其返回码,来控制key的使用;
mean_use_key = random.randint(0, KEY_POOL_NUM_INDICATOR)
for i in range(mean_use_key, KEY_POOL_NUM_INDICATOR, 1):
key = KEY_POOL_LIST[i]
if key == touse_key:
if i == KEY_POOL_NUM_INDICATOR:
change_key()
return
else:
continue
touse_key = key
url = URL_FOR_CHANGE_KEY % (touse_key)
try:
change_key_qps += 1
if change_key_qps % QPS == 0:
sleep(QPS_TIME_UNIT)
r = requests.get(url)
json_ = r.json()
except Exception:
print('requests.get(url)', Exception)
change_key()
return
infocode = json_['infocode']
if not infocode == INFOCODE_OK:
if i == KEY_POOL_NUM_INDICATOR:
sys.exit('NOInvalidKEY')
change_key()
return
return FNAME = '电影院任务列表_20170724.csv'
tosupply_dic = {}
fo = open(FNAME, 'r', encoding='gbk')
file_line_num = 0
for i in fo:
file_line_num += 1
if file_line_num == 1:
continue
tosupply_dic[file_line_num] = {}
is_from_past_line = 1 if len(i.split(',,,,,,,,')) > 1 else 0
l = i.replace('\n', '').replace(',,,,,,,', '').split(',')
dic_ = {}
dic_['sequence_number'] = l[0]
dic_['area'] = l[1] if is_from_past_line == 0 else tosupply_dic[file_line_num - 1]['area']
dic_['province'] = l[2] if is_from_past_line == 0 else tosupply_dic[file_line_num - 1][
'province']
dic_['city'] = l[3] if is_from_past_line == 0 else tosupply_dic[file_line_num - 1]['city']
dic_['district'] = ''
dic_['address'] = ''
dic_['buliding'] = ''
dic_['longitude_latitude'] = ''
dic_['busniess_type'] = l[8] if is_from_past_line == 0 else l[1]
dic_['name'] = l[9] if is_from_past_line == 0 else l[2]
dic_['parent_company'] = l[10] if is_from_past_line == 0 else tosupply_dic[file_line_num - 1]['parent_company']
dic_['is_from_past_line'] = is_from_past_line
dic_['gd_name'] = ''
dic_['gd_city'] = ''
tosupply_dic[file_line_num] = dic_ EACH_THREAD_REQUEST_NUM = 30
exception_line_num_list = [] # keywords = '&keywords='
# OFFSET = '&offset=1'
# CITYLIMIT = '&citylimit=true'
# # 080601 体育休闲服务 影剧院 电影院
# POI_TYPES = '&types=080601'
#
# http://restapi.amap.com/v3/place/text?key=&keywords=重庆万盛DAV国际影城&city=重庆&types=080601&offset=1&citylimit=true
requests_counter = 0
tosupply_dic_len = len(tosupply_dic)
tosupply_dic_len_ = tosupply_dic_len - 1 # thread_strat_file_line_num
def supply_dic(thread_strat_file_line_num):
global tosupply_dic, requests_counter, tosupply_dic_len_, exception_line_num_list
for loop in range(0, EACH_THREAD_REQUEST_NUM, 1):
file_line_num = thread_strat_file_line_num + loop
if file_line_num - 2 > tosupply_dic_len_:
return
if file_line_num < 2 or len(tosupply_dic[file_line_num]['district']) > 0:
if file_line_num in exception_line_num_list:
list_index = exception_line_num_list.index(file_line_num)
del exception_line_num_list[list_index]
continue
dic_ = tosupply_dic[file_line_num]
city = dic_['city']
name = dic_['name']
url = '%s?key=%s&keywords=%s&city=%s%s%s%s' % (URL_TYPE, touse_key, name, city, POI_TYPES, OFFSET, CITYLIMIT)
if requests_counter % QPS == 0:
sleep(QPS_TIME_UNIT)
try:
r = requests.get(url)
r_json = r.json()
except Exception:
if file_line_num not in exception_line_num_list:
exception_line_num_list.append(file_line_num)
continue
infocode = r_json['infocode']
if infocode == '':
count = r_json['count']
if int(count) > 0:
pois_list = r_json['pois']
pos_dic = pois_list[0]
tosupply_dic[file_line_num]['district'] = pos_dic['adname'] if len(pos_dic['address']) <= 2:
print(pos_dic)
print(pos_dic['address'])
tosupply_dic[file_line_num]['address'] = pos_dic['address'] if len(pos_dic['address']) > 2 else '高德缺地址'
if len(pos_dic['address']) <= 2:
print(tosupply_dic[file_line_num]['address'])
tosupply_dic[file_line_num]['longitude_latitude'] = pos_dic['location']
tosupply_dic[file_line_num]['gd_name'] = pos_dic['name']
tosupply_dic[file_line_num]['gd_city'] = pos_dic['cityname'] elif int(count) == 0:
tosupply_dic[file_line_num]['gd_name'] = 'GD-NO-DATA'
if file_line_num in exception_line_num_list:
list_index = exception_line_num_list.index(file_line_num)
del exception_line_num_list[list_index]
else:
if file_line_num not in exception_line_num_list:
exception_line_num_list.append(file_line_num)
change_key() MAX_EXCEPTION_URL_NUM = 0 def deal_exception_list():
global exception_line_num_list
print(exception_line_num_list)
if len(exception_line_num_list) > MAX_EXCEPTION_URL_NUM:
for thread_strat_file_line_num in exception_line_num_list:
supply_dic(thread_strat_file_line_num)
else:
return
deal_exception_list() class MyThread(threading.Thread):
def __init__(self, func, args, name=''):
threading.Thread.__init__(self)
self.name = name
self.func = func
self.args = args def run(self):
self.func(self.args) def gen_building(str):
start_ = 0
end_ = 0
if str.find('号') > -1:
start_ = str.find('号') + 1
elif str.find('路') > -1:
start_ = str.find('路') + 1
elif str.find('道') > -1:
start_ = str.find('道') + 1 if str.find('层') > -1:
end_ = str.find('层') + 1
elif str.find('楼') > -1:
end_ = str.find('楼') + 1 if end_ - start_ > 3:
return ''.join((list(str)[start_:end_]))
else:
return '' def main():
print('starting at:', ctime())
threads_list = []
thread_sum = math.ceil(tosupply_dic_len / EACH_THREAD_REQUEST_NUM)
print(185, thread_sum)
for nloop in range(0, thread_sum, 1):
thread_strat_file_line_num = nloop * EACH_THREAD_REQUEST_NUM
print(thread_strat_file_line_num)
thread_instance = MyThread(supply_dic, (thread_strat_file_line_num), supply_dic.__name__)
threads_list.append(thread_instance)
# 主进程将在所有非守护进程退出后,退出
for t in threads_list:
t.setDaemon = False
t.start()
# wait for all thrades to finish
for t in threads_list:
t.join()
# pprint.pprint(res_dic) deal_exception_list()
for i in exception_line_num_list:
print('EXCEPTION', i)
FGEN = '电影院任务列表_20170724_新增列_已计算楼宇.csv'
fo = open(FGEN, 'w', encoding='utf-8-sig')
fo.write('序号,地理区域,省份,城市,区域,地址,所属楼宇,经纬度,商圈属性,店铺名,所属院线,is_from_past_line,gd_name,gd_city\n')
fo.closed
fo = open(FGEN, 'a', encoding='utf-8-sig')
for file_line_num in tosupply_dic:
if file_line_num == 1:
continue
dic_ = tosupply_dic[file_line_num]
str = '%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s\n' % (
dic_['sequence_number'], dic_['area'], dic_['province'], dic_['city'], dic_['district'],
dic_['address'].replace(',', ' '),
gen_building(dic_['address']), dic_['longitude_latitude'].replace(',', ' '), dic_['busniess_type'],
dic_['name'],
dic_['parent_company'],
dic_['is_from_past_line'], dic_['gd_name'], dic_['gd_city'])
fo.write(str)
fo.closed if __name__ == '__main__':
main()
{'id': 'B02DD0R6M6', 'name': '横店电影城(大汉店)', 'type': '体育休闲服务;影剧院;电影院', 'typecode': '', 'biz_type': 'cinema', 'address': [], 'location': '113.149267,27.838133', 'tel': '0731-22915555', 'distance': [], 'biz_ext': [], 'pname': '湖南省', 'cityname': '株洲市', 'adname': '芦淞区', 'importance': [], 'shopid': [], 'shopinfo': '', 'poiweight': []}
[]
高德缺地址
{'id': 'B0FFGJYCPN', 'name': '横店电影城(原阳店)', 'type': '体育休闲服务;影剧院;电影院', 'typecode': '', 'biz_type': 'cinema', 'address': [], 'location': '113.960307,35.065736', 'tel': '0373-5911199', 'distance': [], 'biz_ext': [], 'pname': '河南省', 'cityname': '新乡市', 'adname': '原阳县', 'importance': [], 'shopid': [], 'shopinfo': '', 'poiweight': []}
[]
高德缺地址
{'id': 'B0FFH0368R', 'name': '横店电影城', 'type': '体育休闲服务;影剧院;电影院', 'typecode': '', 'biz_type': 'cinema', 'address': [], 'location': '118.430053,29.862110', 'tel': [], 'distance': [], 'biz_ext': [], 'pname': '安徽省', 'cityname': '黄山市', 'adname': '歙县', 'importance': [], 'shopid': [], 'shopinfo': '', 'poiweight': []}
[]
高德缺地址
[, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ]
[, , , , , , , , , , , , , , , , , , , , ]
if url in exception_url_list:
l_index = exception_url_list.index(url)
print(139, 'del')
del exception_url_list[l_index] class MyThread(threading.Thread):
def __init__(self, func, args, name=''):
threading.Thread.__init__(self)
self.name = name
self.func = func
self.args = args def run(self):
self.func(self.args) MAX_EXCEPTION_URL_NUM = 60 def deal_exception_url_list():
global exception_url_list
if len(exception_url_list) > MAX_EXCEPTION_URL_NUM:
for url in exception_url_list:
grab_one_url(url)
else:
return
deal_exception_url_list()
# -*- coding: UTF-8 -*- import math
import random
import re
import sys
import threading
from time import ctime, sleep
from lxml import etree
import pprint
import requests BASE_URL = 'https://www.dianping.com/'
url_district_list = []
GLUE = 'search'
f = open('spider_深圳_district_bussi-nav_url_list - 副本.txt', 'r', encoding='utf-8')
f.closed
SCALA = 'SCALA'
for i in f:
URL_POOL = i.split(SCALA)
break URL_POOL_LEN = len(URL_POOL)
URL_NUM_EACH_THREAD = 1
# {url:{}}
res_dic = {} MAX_PAGE_NUM = 50
QPS = 30
request_counter = 0
QPS_TIME_UNIT = 1 # url = '%s%s%sp%s' % (BASE_URL, GLUE, URL_POOL[1], 3)
# print(url)
# r = requests.get(url)
# html = r.text
# selector = etree.HTML(html)
# page_title = selector.xpath('//title/text()')
# page_Keywords = selector.xpath('//meta[@name="Keywords"]')[0].attrib['content']
# data_ga_index_1 = selector.xpath('.//a[@data-ga-index="1"]/span/text()')[0]
# data_ga_index_2 = selector.xpath('.//a[@data-ga-index="2"]/span/text()')[0]
# data_ga_index_3 = selector.xpath('.//a[@data-ga-index="3"]/span/text()')[0]
# res_dic[url] = {}
# res_dic[url]['page_title'] = page_title
# res_dic[url]['page_Keywords'] = page_Keywords
# res_dic[url]['data_ga_index_1'] = data_ga_index_1
# res_dic[url]['data_ga_index_2'] = data_ga_index_2
# res_dic[url]['data_ga_index_3'] = data_ga_index_3
#
# name_l = selector.xpath('.//li[@class=""]//h4/text()')
#
# mean_price_l = selector.xpath('.//li[@class=""]//a[@class="mean-price"]/b/text()')
#
# flavour_l = selector.xpath('.//li[@class=""]//div[@class="tag-addr"]/a[1]/span/text()')
#
# position_l = selector.xpath('.//li[@class=""]//div[@class="tag-addr"]/a[2]/span/text()')
#
# address_l = selector.xpath('.//li[@class=""]//div[@class="tag-addr"]/span/text()')
#
# len_l = len(name_l)
# res_dic[url]['items_num'] = len_l
# res_dic[url]['items_list'] = []
# len_l_ = len_l - 1
# for i in range(0, len_l_, 1):
# d = {}
# d['name'] = name_l[i]
# d['mean_price'] = mean_price_l[i]
# d['flavour'] = flavour_l[i]
# d['position'] = position_l[i]
# d['address'] = address_l[i]
# res_dic[url]['items_list'].append(d)
#
# d = 4 exception_url_list = [] def grab_one_url(url):
global res_dic, request_counter, exception_url_list
if request_counter % QPS == 0:
print(36, 'sleep', request_counter)
sleep(QPS_TIME_UNIT) request_counter += 1
try:
r = requests.get(url)
except Exception:
if url not in exception_url_list:
exception_url_list.append(url)
print(exception_url_list)
return
html = r.text
selector = etree.HTML(html)
page_title = selector.xpath('//title/text()')[0] try:
page_Keywords = selector.xpath('//meta[@name="Keywords"]')[0].attrib['content'].replace(',', '、')
except Exception:
if url not in exception_url_list:
exception_url_list.append(url)
print(exception_url_list)
return data_ga_index_1 = selector.xpath('.//a[@data-ga-index="1"]/span/text()')[0]
data_ga_index_2 = selector.xpath('.//a[@data-ga-index="2"]/span/text()')[0]
data_ga_index_3 = selector.xpath('.//a[@data-ga-index="3"]/span/text()')[0]
res_dic[url] = {}
res_dic[url]['page_title'] = page_title
res_dic[url]['page_Keywords'] = page_Keywords
res_dic[url]['data_ga_index_1'] = data_ga_index_1
res_dic[url]['data_ga_index_2'] = data_ga_index_2
res_dic[url]['data_ga_index_3'] = data_ga_index_3 name_l = selector.xpath('.//li[@class=""]//h4/text()') mean_price_l = selector.xpath('.//li[@class=""]//a[@class="mean-price"]/b/text()') flavour_l = selector.xpath('.//li[@class=""]//div[@class="tag-addr"]/a[1]/span/text()') position_l = selector.xpath('.//li[@class=""]//div[@class="tag-addr"]/a[2]/span/text()') address_l = selector.xpath('.//li[@class=""]//div[@class="tag-addr"]/span/text()') len_l = len(name_l)
res_dic[url]['items_num'] = len_l
res_dic[url]['items_list'] = []
len_l_ = len_l - 1
for i in range(0, len_l_, 1):
d = {}
d['name'] = name_l[i].replace(',', '、')
d['mean_price'] = mean_price_l[i] if len(mean_price_l) - 1 >= i else ''
d['flavour'] = flavour_l[i]
d['position'] = position_l[i]
# https://www.dianping.com/search/category/7/10/r12335p1
d['address'] = address_l[i].replace(',', '、')
res_dic[url]['items_list'].append(d) if url in exception_url_list:
l_index = exception_url_list.index(url)
print(139, 'del')
del exception_url_list[l_index] class MyThread(threading.Thread):
def __init__(self, func, args, name=''):
threading.Thread.__init__(self)
self.name = name
self.func = func
self.args = args def run(self):
self.func(self.args) MAX_EXCEPTION_URL_NUM = 60 def deal_exception_url_list():
global exception_url_list
if len(exception_url_list) > MAX_EXCEPTION_URL_NUM:
for url in exception_url_list:
grab_one_url(url)
else:
return
deal_exception_url_list() def main():
print('starting at:', ctime())
threads_list = []
thread_sum = math.ceil(URL_POOL_LEN / URL_NUM_EACH_THREAD)
for nloop in range(0, URL_POOL_LEN, 1):
for nnloop in range(1, MAX_PAGE_NUM, 1):
url = URL_POOL[nloop]
url = '%s%s%sp%s' % (BASE_URL, GLUE, url, nnloop)
print(62, url)
thread_instance = MyThread(grab_one_url, (url), grab_one_url.__name__)
threads_list.append(thread_instance)
# 主进程将在所有非守护进程退出后,退出
for t in threads_list:
print(70, t)
t.setDaemon = False
t.start()
# wait for all thrades to finish
for t in threads_list:
t.join()
# pprint.pprint(res_dic) deal_exception_url_list() f_name = 'dzdp_基于区-大商圈的餐馆列表-深圳.csv'
f = open(f_name, 'w', encoding='utf-8-sig')
f.write('')
f.closed
f = open(f_name, 'a', encoding='utf-8-sig')
str = 'name,mean_price, flavour, position,address,url,page_title, page_Keywords, data_ga_index_1, data_ga_index_2, data_ga_index_3,\n'
f.write(str)
for url in res_dic:
page_title = res_dic[url]['page_title']
page_Keywords = res_dic[url]['page_Keywords']
data_ga_index_1 = res_dic[url]['data_ga_index_1']
data_ga_index_2 = res_dic[url]['data_ga_index_2']
data_ga_index_3 = res_dic[url]['data_ga_index_3']
for d in res_dic[url]['items_list']:
name = d['name']
mean_price = d['mean_price']
flavour = d['flavour']
position = d['position']
address = d['address']
str = '%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s\n' % (
name, mean_price, flavour, position, address, url, page_title, page_Keywords, data_ga_index_1,
data_ga_index_2, data_ga_index_3)
f.write(str)
f.closed f_name = 'dzdp_基于区-大商圈的餐馆列表-深圳_EXCEPTION_URL.csv'
f = open(f_name, 'w', encoding='utf-8-sig')
f.write('')
f.closed
f = open(f_name, 'a', encoding='utf-8-sig')
for url in exception_url_list:
f.write(url + '\n')
f.closed if __name__ == '__main__':
main()
#
#
# d = 3
# url = ('%s%s%sp%s') % (BASE_URL, GLUE, '/category/7/10/r1949', 100)
# print(url)
#
# #
#
# class MyThread(threading.Thread):
# def __init__(self, func, args, name=''):
# threading.Thread.__init__(self)
# self.name = name
# self.func = func
# self.args = args
#
# def run(self):
# self.func(self.args)
#
#
# def main():
# print('starting at:', ctime())
# threads_list = []
# thread_sum = math.ceil(file_line_list_len / file_jump_step_num)
# print(thread_sum)
# for nloop in range(1, thread_sum, 1):
# print(nloop)
# thread_instance = MyThread(get_exception_logic_split_loop, (nloop), get_exception_logic_split_loop.__name__)
#
# threads_list.append(thread_instance)
# # 主进程将在所有非守护进程退出后,退出
# for t in threads_list:
# print(t)
# t.setDaemon = False
# t.start()
# # wait for all thrades to finish
# for t in threads_list:
# t.join()
# f_name = 'ALL.csv'
# f = open(f_name, 'w', encoding='utf-8-sig')
# f.write('')
# f.closed
# f = open(f_name, 'a', encoding='utf-8-sig')
# str = 'city, district, name, address, if_in_business_area, if_in_business_area_criterion,catering_kind, average_price, data_from\n'
# f.write(str)
# ## city,district,address,name,catering_kind,average_price,data_from
# count_write_rows = 0
# for i in cater_dic:
# city = i
# if city == '城市':
# continue
# for ii in cater_dic[i]:
# district = ii
# for iii in cater_dic[i][ii]:
# name = iii
# for iv in cater_dic[i][ii][iii]:
# address = iv
# catering_kind = cater_dic[i][ii][iii][iv]['catering_kind']
# average_price = cater_dic[i][ii][iii][iv]['average_price']
# if_in_business_area = cater_dic[i][ii][iii][iv]['if_in_business_area']
# if_in_business_area_criterion = cater_dic[i][ii][iii][iv]['if_in_business_area_criterion']
# data_from = cater_dic[i][ii][iii][iv]['data_from']
# str = '%s,%s,%s,%s,%s,%s,%s,%s,%s\n' % (
# city, district, name, address, if_in_business_area, if_in_business_area_criterion,
# catering_kind, average_price, data_from)
# f.write(str)
# count_write_rows += 1
# f.closed
# print(count_write_rows)
#
#
# if __name__ == '__main__':
# main()
#
#
#
#
#
#
#
#
# d = 4
# URL_POOL = f.detach()
#
# # {district:bussi-nav:[page]}
# SPIDER_URL_DISTRICT_DIC = {}
# for i in f:
# d = i.replace('\n', '').replace(' ', '')
# if d.find(GLUE) > -1:
# dd = d.split(GLUE)[1].split('\"')[0]
# SPIDER_URL_DISTRICT_DIC[dd] = []
# QPS = 50
# TIME_UNIT = 1
# qps_counter = 0
# for k in SPIDER_URL_DISTRICT_DIC:
# url = '%s%s%s' % (BASE_URL, GLUE, k)
# print(url)
# qps_counter += 1
# if qps_counter % QPS == 0:
# sleep(TIME_UNIT)
# try:
# r = requests.get(url)
# print(r.status_code)
# txt = r.text.replace('\r', '').replace(' ', '').split('\n')
# start_flag = 0
# for d in txt:
# if d.find('id="bussi-nav') > -1:
# start_flag = 1
# else:
# if start_flag == 1:
# if d.find('/div') > -1:
# start_flag = 0
# else:
# dd = d.split(GLUE)[1].split('\"')[0]
# SPIDER_URL_DISTRICT_DIC[k].append(dd)
# print(dd)
# except Exception:
# # 修改为,2个函数,递归请求
# print('EXCEPTION', url)
# print(Exception)
#
# SCALA = 'SCALA'
# str = ''
# for k in SPIDER_URL_DISTRICT_DIC:
# for url in SPIDER_URL_DISTRICT_DIC[k]:
# str += SCALA + url
# print(str)
# str = str[5:]
# print(str)
# f = open('spider_深圳_district_bussi-nav_url_list.txt', 'w', encoding='utf-8')
# f.write(str)
# f.closed
#
# d = 5
#
# d = 3
#
# url = 'https://www.dianping.com/search/category/7/10/r29'
# r = requests.get(url)
#
# d = 5
# ZHITONGZI_CITY_DIC = {}
# f = open('直筒子市_东莞中山.txt', 'r', encoding='utf-8')
# ZHITONGZI_CITY_DIC['东莞市'] = []
# ZHITONGZI_CITY_DIC['中山市'] = []
# c = 0
# for i in f:
# ii = i.split(';')
# for iii in ii:
# iv = iii.split('、')
# if len(iv) > 2:
# c += 1
# for v in iv:
# if v.find('(') > -1:
# v_ = v.split('(')[1]
# elif v.find(')') > -1:
# v_ = v.split(')')[0]
# else:
# v_ = v
# if c == 1 or c == 2:
# ZHITONGZI_CITY_DIC['东莞市'].append(v_)
# elif c == 3 or c == 4:
# ZHITONGZI_CITY_DIC['中山市'].append(v_)
# f.closed
#
#
# def chk_is_coffee(str):
# l_ = ['coffee', 'coffe', 'cafe', 'café', 'starbucks', 'caffé']
# # 上岛花式铁板烧 日本菜
# # 泛太平洋大酒店面馆 其他
# l_b = ['咖啡', '星巴克']
# # 星巴克
# for i in l_:
# if str.upper().find(i.upper()) != -1:
# return True
# for i in l_b:
# if str.find(i) != -1:
# return True
# return False
#
#
# def chk_kfc_mdl(str):
# if str.find(u"麦当劳") != -1:
# return 1
# elif str.find(u"肯德基") != -1 or str.upper().find(u"KFC") != -1:
# return 0
# else:
# return 2
#
#
# def get_name(str):
# if str.find("麦当劳") != -1:
# return '麦当劳'
# elif str.find("肯德基") != -1 or str.upper().find(u"KFC") != -1:
# return '肯德基'
# else:
# # str = '狗不理包子(前门店)'
# # str = '(清真)三羊水饺(新民路店)'
# # | 添椒 | 潮涮三国IP火锅
# if str.find('(') == -1 and str.find('(') == -1:
# return str
# res = str.strip(' ').split('(')[0].strip(' ')
# if len(res) == 0:
# try:
# res = str.split(')')[1].split('(')[0]
# except Exception:
# print(Exception)
# # 一锅两头牛(烟青路店)
# res_b = res
# try:
# res_b = res.split('(')[0]
# except Exception:
# print(Exception)
#
# return res_b
#
#
# def chk_city_district(str):
# city_district = str.replace(' ', '')
# if re.match(r".*[a-zA-Z0-9]", city_district) is not None:
# return False
# elif str.find("[") != -1 or str.find("(") != -1 or str.find(")") != -1:
# return False
# else:
# return city_district
#
#
# def chk_catering_kind(str):
# catering_kind = str.replace(' ', '')
# if re.match(r".*[0-9]", catering_kind) is not None:
# return False
# else:
# return catering_kind
#
#
# # ['a','',' ']
# def chk_list_thickness(list_):
# if len(list_) == 0:
# return False
# res_list = []
# for i in list_:
# i_b = i.replace(' ', '')
# if i.replace(' ', '') == '':
# return False
# else:
# res_list.append(i_b)
# return res_list
#
#
# business_area_tag_list = ['大厦', '大楼', '大厦', '百货', '购物中心', '商业中心', 'MALL', '广场', '商场', '单元', '栋', '座', '楼', '层', '底商']
#
#
# def chk_in_business_area(str):
# global business_area_tag_list
# for i in business_area_tag_list:
# if str.find(i) > -1:
# return 1
# return 0
#
#
# # MAX_OFFSET = 25
# # OFFSET = MAX_OFFSET - 1
# MAX_PAGINATION = 100
# pagination = MAX_PAGINATION
# QPS = 50
# TIME_UNIT = 1
# # http://lbs.amap.com/api/webservice/guide/tools/info
# INFOCODE_OK = '10000'
# file_name_key_pool = 'key_pool.pool'
# KEY_POOL_LIST = []
# touse_key = ''
# f = open(file_name_key_pool, 'r', encoding='utf-8')
# for i in f:
# try:
# list_ = i.split('\t')
# key = i.split('\t')[1].split()
# KEY_POOL_LIST.append(key[0])
# except Exception:
# print(Exception)
# KEY_POOL_NUM_INDICATOR = len(KEY_POOL_LIST) - 1
#
# # 北京市 西城区 金堂羊蝎子火锅 真武庙四条1号
# # http://restapi.amap.com/v3/place/around?parameters
# URL_TYPE = 'http://restapi.amap.com/v3/place/text'
# # URL_TYPE = 'http://restapi.amap.com/v3/around'
# touse_key = ''
# RADIUS = '&radius=20'
# keywords = '&keywords='
# OFFSET = '&offset=10'
# CITYLIMIT = '&citylimit=true'
#
# URL_FOR_CHANGE_KEY = 'http://restapi.amap.com/v3/place/text?key=%s&types=060100&city=010&OFFSET=1'
#
# change_key_qps = 0
#
#
# def change_key():
# global touse_key, change_key_qps
#
# # 高德没有遵守自己的QPS/日限策略;所不能通过其返回码,来控制key的使用;
# mean_use_key = random.randint(0, KEY_POOL_NUM_INDICATOR)
# for i in range(mean_use_key, KEY_POOL_NUM_INDICATOR, 1):
# key = KEY_POOL_LIST[i]
# if key == touse_key:
# if i == KEY_POOL_NUM_INDICATOR:
# change_key()
# return
# else:
# continue
# touse_key = key
# url = URL_FOR_CHANGE_KEY % (touse_key)
# try:
# change_key_qps += 1
# if change_key_qps % QPS == 0:
# sleep(TIME_UNIT)
# r = requests.get(url)
# json_ = r.json()
# except Exception:
# print('requests.get(url)', Exception)
# change_key()
# return
# infocode = json_['infocode']
# if not infocode == INFOCODE_OK:
# if i == KEY_POOL_NUM_INDICATOR:
# sys.exit('NOInvalidKEY')
# change_key()
# return
# return
#
#
#
# # 060101 购物服务 商场 购物中心
#
#
# FILTER_GD_BUSINESS_AREA_TYPE_LIST = ['购物中心']
#
#
# def fliter_gd_business_area_type(url):
# global FILTER_GD_BUSINESS_AREA_TYPE_LIST
# # {"suggestion":{"keywords":{},"cities":{}},"info":"OK","status":"1","count":"1","pois":[{"typecode":"050118","adname":"西城区","biz_type":"diner","id":"B0FFG8RYC7","pname":"北京市","importance":{},"location":"116.393715,39.957242","distance":{},"tel":"18600185618","biz_ext":{},"shopid":{},"address":"德胜街道六铺炕北小街8-1号","poiweight":{},"cityname":"北京市","type":"餐饮服务;中餐厅;特色\/地方风味餐厅","shopinfo":"0","name":"炙热青春"}],"infocode":"10000"
# try:
# r = requests.get(url)
# r_json = r.json()
# except Exception:
# print(203, Exception)
# # 返回数据解析json异常
# return 3
# infocode = r_json['infocode']
# if infocode == '10000':
# count = r_json['count']
# if int(count) > 0:
# pois_list = r_json['pois']
# for l in pois_list:
# type = l['type']
# for chk_type in FILTER_GD_BUSINESS_AREA_TYPE_LIST:
# if type.find(chk_type) > -1:
# return 1
# else:
# change_key()
# return 0
#
#
# # f = open('MEITUAN_DAZHONG_20170704.csv', 'r', encoding='gbk')
# # f_2 = open('MEITUAN_DAZHONG_20170705.csv', 'r', encoding='gbk')
# # f_gd = open('GD_POI_KFC_MC.csv', 'r', encoding='utf-8-sig')
#
# # 市key-区key-品牌名key-地址key-{菜类,均价,data_from}
# # {city:{district:{name:{address:{catering_kind,average_price,data_from}}}}}
# cater_dic = {}
# # [{city,district,address,name,catering_kind,average_price,data_from}]
# cater_exception_list = []
# count_catering = 0
# count_catering_exception = 0
#
# coffee_list = []
# count_coffee = 0
#
# fo = open('MEITUAN_DAZHONG_20170705 - 副本.csv', 'r')
#
# file_line_list = []
# for i in fo:
# file_line_list.append(i)
# fo.closed
# #
# # fo = open('MEITUAN_DAZHONG_20170705 - 副本.csv', 'r')
# # while fo.readline():
# # file_line_list_b.append(fo.readline())
# file_line_list_len = len(file_line_list)
# file_jump_step_num = 2000
# count_catering_exception = 0
# count_coffee = 0
# count_catering = 0
#
#
# def get_exception_logic_split_loop(nloop):
# global touse_key, cater_dic, file_line_list, file_line_list_len, file_jump_step_num, count_catering_exception, count_coffee, count_catering
# start_line = nloop * file_jump_step_num
# if start_line >= file_line_list_len:
# print('last-line')
# return
# else:
# start_line_count = 0
# end_line = start_line + file_jump_step_num
# if end_line >= file_line_list_len:
# end_line = file_line_list_len - 1
# for i in range(start_line, end_line, 1):
# l_ = file_line_list[i].replace('\n', '').split(',')
# city = l_[0]
# district = l_[1]
# address = l_[2]
# name = l_[3]
# average_price = l_[4]
# catering_kind = l_[5]
# data_from = 'mtdz_5'
# # 数据准备层
# # 数据运算层
# # 该层处理从目标文件取出的字段列表
# focus_list = [city, district, address, name, catering_kind, average_price, data_from]
# dic_exception = {}
# dic_exception['data_from'] = data_from
# dic_exception['city'] = city
# dic_exception['district'] = district
# dic_exception['name'] = name
# dic_exception['address'] = address
# dic_exception['catering_kind'] = catering_kind
# dic_exception['average_price'] = average_price
#
# if not chk_list_thickness(focus_list) or not chk_city_district(city) or not chk_city_district(
# district) or not chk_catering_kind(catering_kind):
# count_catering_exception += 1
# cater_exception_list.append(dic_exception)
# else:
# name = get_name(name)
#
# m = chk_is_coffee(name)
# # if m:
# # print(list_)
# if not m:
# m = chk_is_coffee(catering_kind)
# if m:
# count_coffee += 1
# coffee_list.append(dic_exception)
#
# if not m:
# dic_details = {}
# dic_details['data_from'] = data_from
# dic_details['catering_kind'] = catering_kind
# dic_details['average_price'] = average_price
# if_in_business_area = chk_in_business_area(address)
# if_in_business_area_criterion = 'str_match'
# if if_in_business_area == 0:
# city_r = '&city=' + district
# keywords = '&keywords=' + address + '|' + name
# start_line_count += 1
# print(start_line, start_line_count)
# if start_line_count % QPS == 0:
# print('sleep')
# sleep(1)
# url = URL_TYPE + '?' + 'key=' + touse_key + RADIUS + keywords + city_r + CITYLIMIT
#
# if_in_business_area = fliter_gd_business_area_type(url)
# if_in_business_area_criterion = 'str_match+request_api'
#
# dic_details['if_in_business_area_criterion'] = if_in_business_area_criterion
# dic_details['if_in_business_area'] = if_in_business_area
#
# if city not in cater_dic:
# cater_dic[city] = {}
# if district not in cater_dic[city]:
# cater_dic[city][district] = {}
# if name not in cater_dic[city][district]:
# cater_dic[city][district][name] = {}
# if address not in cater_dic[city][district][name]:
# cater_dic[city][district][name][address] = {}
#
# cater_dic[city][district][name][address] = dic_details
# count_catering += 1
#
#
# class MyThread(threading.Thread):
# def __init__(self, func, args, name=''):
# threading.Thread.__init__(self)
# self.name = name
# self.func = func
# self.args = args
#
# def run(self):
# self.func(self.args)
#
#
# def main():
# print('starting at:', ctime())
# threads_list = []
# thread_sum = math.ceil(file_line_list_len / file_jump_step_num)
# print(thread_sum)
# for nloop in range(1, thread_sum, 1):
# print(nloop)
# thread_instance = MyThread(get_exception_logic_split_loop, (nloop), get_exception_logic_split_loop.__name__)
#
# threads_list.append(thread_instance)
# # 主进程将在所有非守护进程退出后,退出
# for t in threads_list:
# print(t)
# t.setDaemon = False
# t.start()
# # wait for all thrades to finish
# for t in threads_list:
# t.join()
# f_name = 'ALL.csv'
# f = open(f_name, 'w', encoding='utf-8-sig')
# f.write('')
# f.closed
# f = open(f_name, 'a', encoding='utf-8-sig')
# str = 'city, district, name, address, if_in_business_area, if_in_business_area_criterion,catering_kind, average_price, data_from\n'
# f.write(str)
# ## city,district,address,name,catering_kind,average_price,data_from
# count_write_rows = 0
# for i in cater_dic:
# city = i
# if city == '城市':
# continue
# for ii in cater_dic[i]:
# district = ii
# for iii in cater_dic[i][ii]:
# name = iii
# for iv in cater_dic[i][ii][iii]:
# address = iv
# catering_kind = cater_dic[i][ii][iii][iv]['catering_kind']
# average_price = cater_dic[i][ii][iii][iv]['average_price']
# if_in_business_area = cater_dic[i][ii][iii][iv]['if_in_business_area']
# if_in_business_area_criterion = cater_dic[i][ii][iii][iv]['if_in_business_area_criterion']
# data_from = cater_dic[i][ii][iii][iv]['data_from']
# str = '%s,%s,%s,%s,%s,%s,%s,%s,%s\n' % (
# city, district, name, address, if_in_business_area, if_in_business_area_criterion,
# catering_kind, average_price, data_from)
# f.write(str)
# count_write_rows += 1
# f.closed
# print(count_write_rows)
#
#
# if __name__ == '__main__':
# main()
82000 277
186000 345
42000 251
186000 346
186000 347
42000 252
82000 278
42000 253
42000 254
40000 346
40000 347
42000 255
40000 348
42000 256
40000 349
82000 279
40000 350
sleep
72000 279
12000 350
sleep
72000 280
72000 281
72000 282
96000 274
72000 283
96000 275
186000 348
72000 284
186000 349
106000 275
132000 328
166000 298
188000 372
60000 336
60000 337
60000 338
60000 339
60000 340
82000 280
42000 257
82000 281
82000 282
60000 341
186000 350
sleep
96000 276
72000 285
72000 286
40000 351
72000 287
96000 277
96000 278
72000 288
72000 289
96000 279
72000 290
96000 280
72000 291
96000 281
72000 292
2000 371
96000 282
102000 255
# -*- coding: UTF-8 -*- import re
import pprint
import json
import time
import math
import sys
import requests
import threading
from time import ctime, sleep
import random ZHITONGZI_CITY_DIC = {}
f = open('直筒子市_东莞中山.txt', 'r', encoding='utf-8')
ZHITONGZI_CITY_DIC['东莞市'] = []
ZHITONGZI_CITY_DIC['中山市'] = []
c = 0
for i in f:
ii = i.split(';')
for iii in ii:
iv = iii.split('、')
if len(iv) > 2:
c += 1
for v in iv:
if v.find('(') > -1:
v_ = v.split('(')[1]
elif v.find(')') > -1:
v_ = v.split(')')[0]
else:
v_ = v
if c == 1 or c == 2:
ZHITONGZI_CITY_DIC['东莞市'].append(v_)
elif c == 3 or c == 4:
ZHITONGZI_CITY_DIC['中山市'].append(v_)
f.closed def chk_is_coffee(str):
l_ = ['coffee', 'coffe', 'cafe', 'café', 'starbucks', 'caffé']
# 上岛花式铁板烧 日本菜
# 泛太平洋大酒店面馆 其他
l_b = ['咖啡', '星巴克']
# 星巴克
for i in l_:
if str.upper().find(i.upper()) != -1:
return True
for i in l_b:
if str.find(i) != -1:
return True
return False def chk_kfc_mdl(str):
if str.find(u"麦当劳") != -1:
return 1
elif str.find(u"肯德基") != -1 or str.upper().find(u"KFC") != -1:
return 0
else:
return 2 def get_name(str):
if str.find("麦当劳") != -1:
return '麦当劳'
elif str.find("肯德基") != -1 or str.upper().find(u"KFC") != -1:
return '肯德基'
else:
# str = '狗不理包子(前门店)'
# str = '(清真)三羊水饺(新民路店)'
# | 添椒 | 潮涮三国IP火锅
if str.find('(') == -1 and str.find('(') == -1:
return str
res = str.strip(' ').split('(')[0].strip(' ')
if len(res) == 0:
try:
res = str.split(')')[1].split('(')[0]
except Exception:
print(Exception)
# 一锅两头牛(烟青路店)
res_b = res
try:
res_b = res.split('(')[0]
except Exception:
print(Exception) return res_b def chk_city_district(str):
city_district = str.replace(' ', '')
if re.match(r".*[a-zA-Z0-9]", city_district) is not None:
return False
elif str.find("[") != -1 or str.find("(") != -1 or str.find(")") != -1:
return False
else:
return city_district def chk_catering_kind(str):
catering_kind = str.replace(' ', '')
if re.match(r".*[0-9]", catering_kind) is not None:
return False
else:
return catering_kind # ['a','',' ']
def chk_list_thickness(list_):
if len(list_) == 0:
return False
res_list = []
for i in list_:
i_b = i.replace(' ', '')
if i.replace(' ', '') == '':
return False
else:
res_list.append(i_b)
return res_list business_area_tag_list = ['大厦', '大楼', '大厦', '百货', '购物中心', '商业中心', 'MALL', '广场', '商场', '单元', '栋', '座', '楼', '层', '底商'] def chk_in_business_area(str):
global business_area_tag_list
for i in business_area_tag_list:
if str.find(i) > -1:
return 1
return 0 # MAX_OFFSET = 25
# OFFSET = MAX_OFFSET - 1
MAX_PAGINATION = 100
pagination = MAX_PAGINATION
QPS = 50
TIME_UNIT = 1
# http://lbs.amap.com/api/webservice/guide/tools/info
INFOCODE_OK = ''
file_name_key_pool = 'key_pool.pool'
KEY_POOL_LIST = []
touse_key = ''
f = open(file_name_key_pool, 'r', encoding='utf-8')
for i in f:
try:
list_ = i.split('\t')
key = i.split('\t')[1].split()
KEY_POOL_LIST.append(key[0])
except Exception:
print(Exception)
KEY_POOL_NUM_INDICATOR = len(KEY_POOL_LIST) - 1 # 北京市 西城区 金堂羊蝎子火锅 真武庙四条1号
# http://restapi.amap.com/v3/place/around?parameters
URL_TYPE = 'http://restapi.amap.com/v3/place/text'
# URL_TYPE = 'http://restapi.amap.com/v3/around'
touse_key = ''
RADIUS = '&radius=20'
keywords = '&keywords='
OFFSET = '&offset=10'
CITYLIMIT = '&citylimit=true' URL_FOR_CHANGE_KEY = 'http://restapi.amap.com/v3/place/text?key=%s&types=060100&city=010&OFFSET=1' change_key_qps = 0 def change_key():
global touse_key, change_key_qps # 高德没有遵守自己的QPS/日限策略;所不能通过其返回码,来控制key的使用;
mean_use_key = random.randint(0, KEY_POOL_NUM_INDICATOR)
for i in range(mean_use_key, KEY_POOL_NUM_INDICATOR, 1):
key = KEY_POOL_LIST[i]
if key == touse_key:
if i == KEY_POOL_NUM_INDICATOR:
change_key()
return
else:
continue
touse_key = key
url = URL_FOR_CHANGE_KEY % (touse_key)
try:
change_key_qps += 1
if change_key_qps % QPS == 0:
sleep(TIME_UNIT)
r = requests.get(url)
json_ = r.json()
except Exception:
print('requests.get(url)', Exception)
change_key()
return
infocode = json_['infocode']
if not infocode == INFOCODE_OK:
if i == KEY_POOL_NUM_INDICATOR:
sys.exit('NOInvalidKEY')
change_key()
return
return # 060101 购物服务 商场 购物中心
FILTER_GD_BUSINESS_AREA_TYPE_LIST = ['购物中心'] def fliter_gd_business_area_type(url):
global FILTER_GD_BUSINESS_AREA_TYPE_LIST
# {"suggestion":{"keywords":{},"cities":{}},"info":"OK","status":"1","count":"1","pois":[{"typecode":"050118","adname":"西城区","biz_type":"diner","id":"B0FFG8RYC7","pname":"北京市","importance":{},"location":"116.393715,39.957242","distance":{},"tel":"18600185618","biz_ext":{},"shopid":{},"address":"德胜街道六铺炕北小街8-1号","poiweight":{},"cityname":"北京市","type":"餐饮服务;中餐厅;特色\/地方风味餐厅","shopinfo":"0","name":"炙热青春"}],"infocode":"10000"
try:
r = requests.get(url)
r_json = r.json()
except Exception:
print(203, Exception)
# 返回数据解析json异常
return 3
infocode = r_json['infocode']
if infocode == '':
count = r_json['count']
if int(count) > 0:
pois_list = r_json['pois']
for l in pois_list:
type = l['type']
for chk_type in FILTER_GD_BUSINESS_AREA_TYPE_LIST:
if type.find(chk_type) > -1:
return 1
else:
change_key()
return 0 # f = open('MEITUAN_DAZHONG_20170704.csv', 'r', encoding='gbk')
# f_2 = open('MEITUAN_DAZHONG_20170705.csv', 'r', encoding='gbk')
# f_gd = open('GD_POI_KFC_MC.csv', 'r', encoding='utf-8-sig') # 市key-区key-品牌名key-地址key-{菜类,均价,data_from}
# {city:{district:{name:{address:{catering_kind,average_price,data_from}}}}}
cater_dic = {}
# [{city,district,address,name,catering_kind,average_price,data_from}]
cater_exception_list = []
count_catering = 0
count_catering_exception = 0 coffee_list = []
count_coffee = 0 fo = open('MEITUAN_DAZHONG_20170705 - 副本.csv', 'r') file_line_list = []
for i in fo:
file_line_list.append(i)
fo.closed
#
# fo = open('MEITUAN_DAZHONG_20170705 - 副本.csv', 'r')
# while fo.readline():
# file_line_list_b.append(fo.readline())
file_line_list_len = len(file_line_list)
file_jump_step_num = 2000
count_catering_exception = 0
count_coffee = 0
count_catering = 0 def get_exception_logic_split_loop(nloop):
global touse_key, cater_dic, file_line_list, file_line_list_len, file_jump_step_num, count_catering_exception, count_coffee, count_catering
start_line = nloop * file_jump_step_num
if start_line >= file_line_list_len:
print('last-line')
return
else:
start_line_count = 0
end_line = start_line + file_jump_step_num
if end_line >= file_line_list_len:
end_line = file_line_list_len - 1
for i in range(start_line, end_line, 1):
l_ = file_line_list[i].replace('\n', '').split(',')
city = l_[0]
district = l_[1]
address = l_[2]
name = l_[3]
average_price = l_[4]
catering_kind = l_[5]
data_from = 'mtdz_5'
# 数据准备层
# 数据运算层
# 该层处理从目标文件取出的字段列表
focus_list = [city, district, address, name, catering_kind, average_price, data_from]
dic_exception = {}
dic_exception['data_from'] = data_from
dic_exception['city'] = city
dic_exception['district'] = district
dic_exception['name'] = name
dic_exception['address'] = address
dic_exception['catering_kind'] = catering_kind
dic_exception['average_price'] = average_price if not chk_list_thickness(focus_list) or not chk_city_district(city) or not chk_city_district(
district) or not chk_catering_kind(catering_kind):
count_catering_exception += 1
cater_exception_list.append(dic_exception)
else:
name = get_name(name) m = chk_is_coffee(name)
# if m:
# print(list_)
if not m:
m = chk_is_coffee(catering_kind)
if m:
count_coffee += 1
coffee_list.append(dic_exception) if not m:
dic_details = {}
dic_details['data_from'] = data_from
dic_details['catering_kind'] = catering_kind
dic_details['average_price'] = average_price
if_in_business_area = chk_in_business_area(address)
if_in_business_area_criterion = 'str_match'
if if_in_business_area == 0:
city_r = '&city=' + district
keywords = '&keywords=' + address + '|' + name
start_line_count += 1
print( start_line, start_line_count)
if start_line_count % QPS == 0:
print('sleep')
sleep(1)
url = URL_TYPE + '?' + 'key=' + touse_key + RADIUS + keywords + city_r + CITYLIMIT if_in_business_area = fliter_gd_business_area_type(url)
if_in_business_area_criterion = 'str_match+request_api' dic_details['if_in_business_area_criterion'] = if_in_business_area_criterion
dic_details['if_in_business_area'] = if_in_business_area if city not in cater_dic:
cater_dic[city] = {}
if district not in cater_dic[city]:
cater_dic[city][district] = {}
if name not in cater_dic[city][district]:
cater_dic[city][district][name] = {}
if address not in cater_dic[city][district][name]:
cater_dic[city][district][name][address] = {} cater_dic[city][district][name][address] = dic_details
count_catering += 1 class MyThread(threading.Thread):
def __init__(self, func, args, name=''):
threading.Thread.__init__(self)
self.name = name
self.func = func
self.args = args def run(self):
self.func(self.args) def main():
print('starting at:', ctime())
threads_list = []
thread_sum = math.ceil(file_line_list_len / file_jump_step_num)
print(thread_sum)
for nloop in range(1, thread_sum, 1):
print(nloop)
thread_instance = MyThread(get_exception_logic_split_loop, (nloop), get_exception_logic_split_loop.__name__) threads_list.append(thread_instance)
# 主进程将在所有非守护进程退出后,退出
for t in threads_list:
print(t)
t.setDaemon = False
t.start()
# wait for all thrades to finish
for t in threads_list:
t.join()
f_name = 'ALL.csv'
f = open(f_name, 'w', encoding='utf-8-sig')
f.write('')
f.closed
f = open(f_name, 'a', encoding='utf-8-sig')
str = 'city, district, name, address, if_in_business_area, if_in_business_area_criterion,catering_kind, average_price, data_from\n'
f.write(str)
## city,district,address,name,catering_kind,average_price,data_from
count_write_rows = 0
for i in cater_dic:
city = i
if city == '城市':
continue
for ii in cater_dic[i]:
district = ii
for iii in cater_dic[i][ii]:
name = iii
for iv in cater_dic[i][ii][iii]:
address = iv
catering_kind = cater_dic[i][ii][iii][iv]['catering_kind']
average_price = cater_dic[i][ii][iii][iv]['average_price']
if_in_business_area = cater_dic[i][ii][iii][iv]['if_in_business_area']
if_in_business_area_criterion = cater_dic[i][ii][iii][iv]['if_in_business_area_criterion']
data_from = cater_dic[i][ii][iii][iv]['data_from']
str = '%s,%s,%s,%s,%s,%s,%s,%s,%s\n' % (
city, district, name, address, if_in_business_area, if_in_business_area_criterion,
catering_kind, average_price, data_from)
f.write(str)
count_write_rows += 1
f.closed
print(count_write_rows) if __name__ == '__main__':
main()
# -*- coding: UTF-8 -*- import re
import pprint
import json
import time
import math
import sys
import requests
import threading
from time import ctime, sleep
import random ZHITONGZI_CITY_DIC = {}
f = open('直筒子市_东莞中山.txt', 'r', encoding='utf-8')
ZHITONGZI_CITY_DIC['东莞市'] = []
ZHITONGZI_CITY_DIC['中山市'] = []
c = 0
for i in f:
ii = i.split(';')
for iii in ii:
iv = iii.split('、')
if len(iv) > 2:
c += 1
for v in iv:
if v.find('(') > -1:
v_ = v.split('(')[1]
elif v.find(')') > -1:
v_ = v.split(')')[0]
else:
v_ = v
if c == 1 or c == 2:
ZHITONGZI_CITY_DIC['东莞市'].append(v_)
elif c == 3 or c == 4:
ZHITONGZI_CITY_DIC['中山市'].append(v_)
f.closed def chk_is_coffee(str):
l_ = ['coffee', 'coffe', 'cafe', 'café', 'starbucks', 'caffé']
# 上岛花式铁板烧 日本菜
# 泛太平洋大酒店面馆 其他
l_b = ['咖啡', '星巴克']
# 星巴克
for i in l_:
if str.upper().find(i.upper()) != -1:
return True
for i in l_b:
if str.find(i) != -1:
return True
return False def chk_kfc_mdl(str):
if str.find(u"麦当劳") != -1:
return 1
elif str.find(u"肯德基") != -1 or str.upper().find(u"KFC") != -1:
return 0
else:
return 2 def get_name(str):
if str.find("麦当劳") != -1:
return '麦当劳'
elif str.find("肯德基") != -1 or str.upper().find(u"KFC") != -1:
return '肯德基'
else:
# str = '狗不理包子(前门店)'
# str = '(清真)三羊水饺(新民路店)'
# | 添椒 | 潮涮三国IP火锅
if str.find('(') == -1 and str.find('(') == -1:
return str
res = str.strip(' ').split('(')[0].strip(' ')
if len(res) == 0:
try:
res = str.split(')')[1].split('(')[0]
except Exception:
print(Exception)
# 一锅两头牛(烟青路店)
res_b = res
try:
res_b = res.split('(')[0]
except Exception:
print(Exception) return res_b def chk_city_district(str):
city_district = str.replace(' ', '')
if re.match(r".*[a-zA-Z0-9]", city_district) is not None:
return False
elif str.find("[") != -1 or str.find("(") != -1 or str.find(")") != -1:
return False
else:
return city_district def chk_catering_kind(str):
catering_kind = str.replace(' ', '')
if re.match(r".*[0-9]", catering_kind) is not None:
return False
else:
return catering_kind # ['a','',' ']
def chk_list_thickness(list_):
if len(list_) == 0:
return False
res_list = []
for i in list_:
i_b = i.replace(' ', '')
if i.replace(' ', '') == '':
return False
else:
res_list.append(i_b)
return res_list business_area_tag_list = ['大厦', '大楼', '大厦', '百货', '购物中心', '商业中心', 'MALL', '广场', '商场', '单元', '栋', '座', '楼', '层', '底商'] def chk_in_business_area(str):
global business_area_tag_list
for i in business_area_tag_list:
if str.find(i) > -1:
return 1
return 0 # MAX_OFFSET = 25
# OFFSET = MAX_OFFSET - 1
MAX_PAGINATION = 100
pagination = MAX_PAGINATION
QPS = 50
TIME_UNIT = 1
# http://lbs.amap.com/api/webservice/guide/tools/info
INFOCODE_OK = ''
file_name_key_pool = 'key_pool.pool'
KEY_POOL_LIST = []
touse_key = ''
f = open(file_name_key_pool, 'r', encoding='utf-8')
for i in f:
try:
list_ = i.split('\t')
key = i.split('\t')[1].split()
KEY_POOL_LIST.append(key[0])
except Exception:
print(Exception)
KEY_POOL_NUM_INDICATOR = len(KEY_POOL_LIST) - 1 # 北京市 西城区 金堂羊蝎子火锅 真武庙四条1号
# http://restapi.amap.com/v3/place/around?parameters
URL_TYPE = 'http://restapi.amap.com/v3/place/text'
# URL_TYPE = 'http://restapi.amap.com/v3/around'
touse_key = ''
RADIUS = '&radius=20'
keywords = '&keywords='
OFFSET = '&offset=10'
CITYLIMIT = '&citylimit=true' URL_FOR_CHANGE_KEY = 'http://restapi.amap.com/v3/place/text?key=%s&types=060100&city=010&OFFSET=1' change_key_qps = 0 def change_key():
global touse_key, change_key_qps # 高德没有遵守自己的QPS/日限策略;所不能通过其返回码,来控制key的使用;
mean_use_key = random.randint(0, KEY_POOL_NUM_INDICATOR)
for i in range(mean_use_key, KEY_POOL_NUM_INDICATOR, 1):
key = KEY_POOL_LIST[i]
if key == touse_key:
if i == KEY_POOL_NUM_INDICATOR:
change_key()
return
else:
continue
touse_key = key
url = URL_FOR_CHANGE_KEY % (touse_key)
try:
change_key_qps += 1
if change_key_qps % QPS == 0:
sleep(TIME_UNIT)
r = requests.get(url)
json_ = r.json()
except Exception:
print('requests.get(url)', Exception)
change_key()
return
infocode = json_['infocode']
if not infocode == INFOCODE_OK:
if i == KEY_POOL_NUM_INDICATOR:
sys.exit('NOInvalidKEY')
change_key()
return
return # 060101 购物服务 商场 购物中心
FILTER_GD_BUSINESS_AREA_TYPE_LIST = ['购物中心'] def fliter_gd_business_area_type(url):
global FILTER_GD_BUSINESS_AREA_TYPE_LIST
# {"suggestion":{"keywords":{},"cities":{}},"info":"OK","status":"1","count":"1","pois":[{"typecode":"050118","adname":"西城区","biz_type":"diner","id":"B0FFG8RYC7","pname":"北京市","importance":{},"location":"116.393715,39.957242","distance":{},"tel":"18600185618","biz_ext":{},"shopid":{},"address":"德胜街道六铺炕北小街8-1号","poiweight":{},"cityname":"北京市","type":"餐饮服务;中餐厅;特色\/地方风味餐厅","shopinfo":"0","name":"炙热青春"}],"infocode":"10000"
try:
r = requests.get(url)
r_json = r.json()
except Exception:
print(203, Exception)
# 返回数据解析json异常
return 3
infocode = r_json['infocode']
if infocode == '':
count = r_json['count']
if int(count) > 0:
pois_list = r_json['pois']
for l in pois_list:
type = l['type']
for chk_type in FILTER_GD_BUSINESS_AREA_TYPE_LIST:
if type.find(chk_type) > -1:
return 1
else:
change_key()
return 0 # f = open('MEITUAN_DAZHONG_20170704.csv', 'r', encoding='gbk')
# f_2 = open('MEITUAN_DAZHONG_20170705.csv', 'r', encoding='gbk')
# f_gd = open('GD_POI_KFC_MC.csv', 'r', encoding='utf-8-sig') # 市key-区key-品牌名key-地址key-{菜类,均价,data_from}
# {city:{district:{name:{address:{catering_kind,average_price,data_from}}}}}
cater_dic = {}
# [{city,district,address,name,catering_kind,average_price,data_from}]
cater_exception_list = []
count_catering = 0
count_catering_exception = 0 coffee_list = []
count_coffee = 0 fo = open('MEITUAN_DAZHONG_20170705 - 副本.csv', 'r') file_line_list = []
for i in fo:
file_line_list.append(i)
fo.closed
#
# fo = open('MEITUAN_DAZHONG_20170705 - 副本.csv', 'r')
# while fo.readline():
# file_line_list_b.append(fo.readline())
file_line_list_len = len(file_line_list)
file_jump_step_num = 4000
count_catering_exception = 0
count_coffee = 0
count_catering = 0 def get_exception_logic_split_loop(nloop):
print(247, nloop)
global touse_key, cater_dic, file_line_list, file_line_list_len, file_jump_step_num, count_catering_exception, count_coffee, count_catering
start_line = nloop * file_jump_step_num
if start_line >= file_line_list_len:
print('last-line')
return
else:
start_line_count = 0
end_line = start_line + file_jump_step_num
if end_line >= file_line_list_len:
end_line = file_line_list_len - 1
for i in range(start_line, end_line, 1):
l_ = file_line_list[i].replace('\n', '').split(',')
city = l_[0]
district = l_[1]
address = l_[2]
name = l_[3]
average_price = l_[4]
catering_kind = l_[5]
data_from = 'mtdz_5'
# 数据准备层
# 数据运算层
# 该层处理从目标文件取出的字段列表
focus_list = [city, district, address, name, catering_kind, average_price, data_from]
dic_exception = {}
dic_exception['data_from'] = data_from
dic_exception['city'] = city
dic_exception['district'] = district
dic_exception['name'] = name
dic_exception['address'] = address
dic_exception['catering_kind'] = catering_kind
dic_exception['average_price'] = average_price if not chk_list_thickness(focus_list) or not chk_city_district(city) or not chk_city_district(
district) or not chk_catering_kind(catering_kind):
count_catering_exception += 1
cater_exception_list.append(dic_exception)
else:
name = get_name(name) m = chk_is_coffee(name)
# if m:
# print(list_)
if not m:
m = chk_is_coffee(catering_kind)
if m:
count_coffee += 1
coffee_list.append(dic_exception) if not m:
dic_details = {}
dic_details['data_from'] = data_from
dic_details['catering_kind'] = catering_kind
dic_details['average_price'] = average_price
if_in_business_area = chk_in_business_area(address)
if_in_business_area_criterion = 'str_match'
if if_in_business_area == 0:
city_r = '&city=' + district
keywords = '&keywords=' + address + '|' + name
start_line_count += 1
print(417, start_line, start_line_count)
if start_line_count % QPS == 0:
print('sleep')
sleep(1)
url = URL_TYPE + '?' + 'key=' + touse_key + RADIUS + keywords + city_r + CITYLIMIT if_in_business_area = fliter_gd_business_area_type(url)
if_in_business_area_criterion = 'str_match+request_api' dic_details['if_in_business_area_criterion'] = if_in_business_area_criterion
dic_details['if_in_business_area'] = if_in_business_area if city not in cater_dic:
cater_dic[city] = {}
if district not in cater_dic[city]:
cater_dic[city][district] = {}
if name not in cater_dic[city][district]:
cater_dic[city][district][name] = {}
if address not in cater_dic[city][district][name]:
cater_dic[city][district][name][address] = {} cater_dic[city][district][name][address] = dic_details
count_catering += 1 class MyThread(threading.Thread):
def __init__(self, func, args, name=''):
threading.Thread.__init__(self)
self.name = name
self.func = func
self.args = args def run(self):
self.func(self.args) def main():
print('starting at:', ctime())
threads_list = []
thread_sum = math.ceil(file_line_list_len / file_jump_step_num)
print(thread_sum)
for nloop in range(1, thread_sum, 1):
print(nloop)
thread_instance = MyThread(get_exception_logic_split_loop, (nloop), get_exception_logic_split_loop.__name__)
print(353, '')
threads_list.append(thread_instance)
# 主进程将在所有非守护进程退出后,退出
for t in threads_list:
print(t)
t.setDaemon = False
t.start()
# wait for all thrades to finish
for t in threads_list:
t.join() print(467, cater_dic)
f_name = 'ALL.csv'
f = open(f_name, 'w', encoding='utf-8-sig')
f.write('')
f.closed
f = open(f_name, 'a', encoding='utf-8-sig')
str = 'city, district, name, address, if_in_business_area, if_in_business_area_criterion,catering_kind, average_price, data_from\n'
f.write(str)
## city,district,address,name,catering_kind,average_price,data_from
count_write_rows = 0
for i in cater_dic:
city = i
if city == '城市':
continue
for ii in cater_dic[i]:
district = ii
for iii in cater_dic[i][ii]:
name = iii
for iv in cater_dic[i][ii][iii]:
address = iv
catering_kind = cater_dic[i][ii][iii][iv]['catering_kind']
average_price = cater_dic[i][ii][iii][iv]['average_price']
if_in_business_area = cater_dic[i][ii][iii][iv]['if_in_business_area']
if_in_business_area_criterion = cater_dic[i][ii][iii][iv]['if_in_business_area_criterion']
data_from = cater_dic[i][ii][iii][iv]['data_from']
str = '%s,%s,%s,%s,%s,%s,%s,%s,%s\n' % (
city, district, name, address, if_in_business_area, if_in_business_area_criterion,
catering_kind, average_price, data_from)
f.write(str)
count_write_rows += 1
f.closed
print(count_write_rows) if __name__ == '__main__':
main()
change_key_qps = 0 def change_key():
global touse_key, change_key_qps
change_key_qps += 1
if change_key_qps % QPS == 0:
sleep(TIME_UNIT)
# 高德没有遵守自己的QPS/日限策略;所不能通过其返回码,来控制key的使用;
mean_use_key = random.randint(0, KEY_POOL_NUM_INDICATOR)
print(mean_use_key)
for i in range(mean_use_key, KEY_POOL_NUM_INDICATOR, 1):
key = KEY_POOL_LIST[i]
if key == touse_key:
if i == KEY_POOL_NUM_INDICATOR:
change_key()
else:
continue
print(172, 'present_key', touse_key)
touse_key = key
url = URL_FOR_CHANGE_KEY % (touse_key)
print(175, 'touse_key', touse_key)
try:
r = requests.get(url)
try:
json_ = r.json()
except Exception:
print(' r.json()', Exception)
change_key()
except Exception:
print('requests.get(url)', Exception)
change_key()
infocode = json_['infocode']
if not infocode == INFOCODE_OK:
if i == KEY_POOL_NUM_INDICATOR:
sys.exit('NOInvalidKEY')
change_key()
高德没有遵守自己的QPS/日限策略;所不能通过其返回码,来控制key的使用;
2
172 present_key c5ef87ab7efe0d76b970fd330bf9e7f2
175 touse_key adf8e13d1b170fcef7132ea3178a2d6c
172 present_key adf8e13d1b170fcef7132ea3178a2d6c
175 touse_key 2f3d41dfbce352fc4d82009c552505fe
172 present_key 2f3d41dfbce352fc4d82009c552505fe
175 touse_key c5ef87ab7efe0d76b970fd330bf9e7f2
172 present_key c5ef87ab7efe0d76b970fd330bf9e7f2
175 touse_key 2f3d41dfbce352fc4d82009c552505fe
172 present_key 2f3d41dfbce352fc4d82009c552505fe
175 touse_key c5ef87ab7efe0d76b970fd330bf9e7f2
172 present_key c5ef87ab7efe0d76b970fd330bf9e7f2
175 touse_key 6d95ab3f63c494911002c1734089548a
6
172 present_key 6d95ab3f63c494911002c1734089548a
175 touse_key adf8e13d1b170fcef7132ea3178a2d6c
6
172 present_key adf8e13d1b170fcef7132ea3178a2d6c
175 touse_key 6d95ab3f63c494911002c1734089548a
6
172 present_key 6d95ab3f63c494911002c1734089548a
175 touse_key adf8e13d1b170fcef7132ea3178a2d6c
4
172 present_key adf8e13d1b170fcef7132ea3178a2d6c
175 touse_key c0d76e9fa950d0ff1761d56bd78a902e
def change_key():
global touse_key
mean_use_key = random.randint(0, KEY_POOL_NUM_INDICATOR)
print(mean_use_key)
for i in range(mean_use_key, KEY_POOL_NUM_INDICATOR, 1):
key = KEY_POOL_LIST[i]
if key == touse_key:
continue
print(172, 'present_key', touse_key)
touse_key = key
url = URL_FOR_CHANGE_KEY % (touse_key)
print(175, 'touse_key', touse_key)
try:
r = requests.get(url)
try :
json_ = r.json()
except Exception:
print(' r.json()',Exception)
change_key()
except Exception:
print('requests.get(url)',Exception)
change_key()
infocode = json_['infocode']
if not infocode == INFOCODE_OK:
if i == KEY_POOL_NUM_INDICATOR:
sys.exit('NOInvalidKEY')
change_key()
# -*- coding: UTF-8 -*- import re
import pprint
import json
import time
import math
import sys
import requests
import threading
from time import ctime, sleep ZHITONGZI_CITY_DIC = {}
f = open('直筒子市_东莞中山.txt', 'r', encoding='utf-8')
ZHITONGZI_CITY_DIC['东莞市'] = []
ZHITONGZI_CITY_DIC['中山市'] = []
c = 0
for i in f:
ii = i.split(';')
for iii in ii:
iv = iii.split('、')
if len(iv) > 2:
c += 1
for v in iv:
if v.find('(') > -1:
v_ = v.split('(')[1]
elif v.find(')') > -1:
v_ = v.split(')')[0]
else:
v_ = v
if c == 1 or c == 2:
ZHITONGZI_CITY_DIC['东莞市'].append(v_)
elif c == 3 or c == 4:
ZHITONGZI_CITY_DIC['中山市'].append(v_)
f.closed def chk_is_coffee(str):
l_ = ['coffee', 'coffe', 'cafe', 'café', 'starbucks', 'caffé']
# 上岛花式铁板烧 日本菜
# 泛太平洋大酒店面馆 其他
l_b = ['咖啡', '星巴克']
# 星巴克
for i in l_:
if str.upper().find(i.upper()) != -1:
return True
for i in l_b:
if str.find(i) != -1:
return True
return False def chk_kfc_mdl(str):
if str.find(u"麦当劳") != -1:
return 1
elif str.find(u"肯德基") != -1 or str.upper().find(u"KFC") != -1:
return 0
else:
return 2 def get_name(str):
if str.find("麦当劳") != -1:
return '麦当劳'
elif str.find("肯德基") != -1 or str.upper().find(u"KFC") != -1:
return '肯德基'
else:
# str = '狗不理包子(前门店)'
# str = '(清真)三羊水饺(新民路店)'
# | 添椒 | 潮涮三国IP火锅
if str.find('(') == -1 and str.find('(') == -1:
return str
res = str.strip(' ').split('(')[0].strip(' ')
if len(res) == 0:
try:
res = str.split(')')[1].split('(')[0]
except Exception:
print(Exception)
# 一锅两头牛(烟青路店)
res_b = res
try:
res_b = res.split('(')[0]
except Exception:
print(Exception) return res_b def chk_city_district(str):
city_district = str.replace(' ', '')
if re.match(r".*[a-zA-Z0-9]", city_district) is not None:
return False
elif str.find("[") != -1 or str.find("(") != -1 or str.find(")") != -1:
return False
else:
return city_district def chk_catering_kind(str):
catering_kind = str.replace(' ', '')
if re.match(r".*[0-9]", catering_kind) is not None:
return False
else:
return catering_kind # ['a','',' ']
def chk_list_thickness(list_):
if len(list_) == 0:
return False
res_list = []
for i in list_:
i_b = i.replace(' ', '')
if i.replace(' ', '') == '':
return False
else:
res_list.append(i_b)
return res_list business_area_tag_list = ['大厦', '大楼', '大厦', '百货', '购物中心', '商业中心', 'MALL', '广场', '商场', '单元', '栋', '座', '楼', '层', '底商'] def chk_in_business_area(str):
global business_area_tag_list
for i in business_area_tag_list:
if str.find(i) > -1:
return 1
return 0 # MAX_OFFSET = 25
# OFFSET = MAX_OFFSET - 1
MAX_PAGINATION = 100
pagination = MAX_PAGINATION
QPS = 50
TIME_UNIT = 1
# http://lbs.amap.com/api/webservice/guide/tools/info
INFOCODE_OK = ''
file_name_key_pool = 'key_pool.pool'
KEY_POOL_LIST = []
touse_key = ''
f = open(file_name_key_pool, 'r', encoding='utf-8')
for i in f:
try:
list_ = i.split('\t')
key = i.split('\t')[1].split()
KEY_POOL_LIST.append(key[0])
except Exception:
print(Exception)
KEY_POOL_NUM_INDICATOR = len(KEY_POOL_LIST) - 1 # 北京市 西城区 金堂羊蝎子火锅 真武庙四条1号
# http://restapi.amap.com/v3/place/around?parameters
URL_TYPE = 'http://restapi.amap.com/v3/place/text'
# URL_TYPE = 'http://restapi.amap.com/v3/around'
touse_key = ''
RADIUS = '&radius=20'
keywords = '&keywords='
OFFSET = '&offset=10'
CITYLIMIT = '&citylimit=true' URL_FOR_CHANGE_KEY = 'http://restapi.amap.com/v3/place/text?key=%s&types=060100&city=010&OFFSET=1' def change_key():
global touse_key
for i in range(0, KEY_POOL_NUM_INDICATOR, 1):
key = KEY_POOL_LIST[i]
if key == touse_key:
continue
touse_key = key
url = URL_FOR_CHANGE_KEY % (touse_key)
print(62, 'chk_key', url)
print(62, 'touse_key', touse_key)
try:
r = requests.get(url)
except Exception:
print(Exception)
change_key()
json_ = r.json()
infocode = json_['infocode']
if not infocode == INFOCODE_OK:
if i == KEY_POOL_NUM_INDICATOR:
sys.exit('NOInvalidKEY')
change_key() # 060101 购物服务 商场 购物中心
FILTER_GD_BUSINESS_AREA_TYPE_LIST = ['购物中心'] def fliter_gd_business_area_type(url):
global FILTER_GD_BUSINESS_AREA_TYPE_LIST
# {"suggestion":{"keywords":{},"cities":{}},"info":"OK","status":"1","count":"1","pois":[{"typecode":"050118","adname":"西城区","biz_type":"diner","id":"B0FFG8RYC7","pname":"北京市","importance":{},"location":"116.393715,39.957242","distance":{},"tel":"18600185618","biz_ext":{},"shopid":{},"address":"德胜街道六铺炕北小街8-1号","poiweight":{},"cityname":"北京市","type":"餐饮服务;中餐厅;特色\/地方风味餐厅","shopinfo":"0","name":"炙热青春"}],"infocode":"10000"
try:
r = requests.get(url)
r_json = r.json()
except Exception:
print(Exception)
print(195, url)
return 0
infocode = r_json['infocode']
if infocode == '':
count = r_json['count']
if int(count) > 0:
pois_list = r_json['pois']
for l in pois_list:
type = l['type']
for chk_type in FILTER_GD_BUSINESS_AREA_TYPE_LIST:
if type.find(chk_type) > -1:
return 1
else:
change_key()
return 0 # f = open('MEITUAN_DAZHONG_20170704.csv', 'r', encoding='gbk')
# f_2 = open('MEITUAN_DAZHONG_20170705.csv', 'r', encoding='gbk')
# f_gd = open('GD_POI_KFC_MC.csv', 'r', encoding='utf-8-sig') # 市key-区key-品牌名key-地址key-{菜类,均价,data_from}
# {city:{district:{name:{address:{catering_kind,average_price,data_from}}}}}
cater_dic = {}
# [{city,district,address,name,catering_kind,average_price,data_from}]
cater_exception_list = []
count_catering = 0
count_catering_exception = 0 coffee_list = []
count_coffee = 0 fo = open('MEITUAN_DAZHONG_20170705 - 副本.csv', 'r') file_line_list = []
for i in fo:
file_line_list.append(i)
fo.closed
#
# fo = open('MEITUAN_DAZHONG_20170705 - 副本.csv', 'r')
# while fo.readline():
# file_line_list_b.append(fo.readline())
file_line_list_len = len(file_line_list)
file_jump_step_num = 10000
count_catering_exception = 0
count_coffee = 0
count_catering = 0 def get_exception_logic_split_loop(nloop):
print(247,nloop)
global touse_key,cater_dic, file_line_list, file_line_list_len, file_jump_step_num, count_catering_exception, count_coffee, count_catering
start_line = nloop * file_jump_step_num
if start_line >= file_line_list_len:
print('last-line')
return
else:
start_line_count = 0
end_line = start_line + file_jump_step_num
if end_line >= file_line_list_len:
end_line = file_line_list_len - 1
for i in range(start_line, end_line, 1):
l_ = file_line_list[i].replace('\n', '').split(',')
city = l_[0]
district = l_[1]
address = l_[2]
name = l_[3]
average_price = l_[4]
catering_kind = l_[5]
data_from = 'mtdz_5'
# 数据准备层
# 数据运算层
# 该层处理从目标文件取出的字段列表
focus_list = [city, district, address, name, catering_kind, average_price, data_from]
dic_exception = {}
dic_exception['data_from'] = data_from
dic_exception['city'] = city
dic_exception['district'] = district
dic_exception['name'] = name
dic_exception['address'] = address
dic_exception['catering_kind'] = catering_kind
dic_exception['average_price'] = average_price if not chk_list_thickness(focus_list) or not chk_city_district(city) or not chk_city_district(
district) or not chk_catering_kind(catering_kind):
count_catering_exception += 1
cater_exception_list.append(dic_exception)
else:
name = get_name(name) m = chk_is_coffee(name)
# if m:
# print(list_)
if not m:
m = chk_is_coffee(catering_kind)
if m:
count_coffee += 1
coffee_list.append(dic_exception) if not m:
dic_details = {}
dic_details['data_from'] = data_from
dic_details['catering_kind'] = catering_kind
dic_details['average_price'] = average_price
if_in_business_area = chk_in_business_area(address)
if_in_business_area_criterion = 'str_match'
if if_in_business_area == 0:
city_r = '&city=' + district
keywords = '&keywords=' + address + '|' + name
start_line_count += 1
print(417, start_line,start_line_count)
if start_line_count%QPS == 0:
print('sleep')
sleep(1)
url = URL_TYPE + '?' + 'key=' + touse_key + RADIUS + keywords + city_r + CITYLIMIT if_in_business_area = fliter_gd_business_area_type(url)
if_in_business_area_criterion = 'str_match+request_api' dic_details['if_in_business_area_criterion'] = if_in_business_area_criterion
dic_details['if_in_business_area'] = if_in_business_area if city not in cater_dic:
cater_dic[city] = {}
if district not in cater_dic[city]:
cater_dic[city][district] = {}
if name not in cater_dic[city][district]:
cater_dic[city][district][name] = {}
if address not in cater_dic[city][district][name]:
cater_dic[city][district][name][address] = {} cater_dic[city][district][name][address] = dic_details
count_catering += 1 class MyThread(threading.Thread):
def __init__(self,func,args,name=''):
threading.Thread.__init__(self)
self.name = name
self.func = func
self.args = args
def run(self):
self.func(self.args) def main():
print('starting at:',ctime())
threads_list = []
thread_sum = math.ceil(file_line_list_len / file_jump_step_num)
print(thread_sum)
for nloop in range(1, thread_sum, 1):
print(nloop)
thread_instance = MyThread(get_exception_logic_split_loop,(nloop),get_exception_logic_split_loop.__name__)
print(353,'')
threads_list.append(thread_instance)
# 主进程将在所有非守护进程退出后,退出
for t in threads_list:
print(t)
t.setDaemon = False
t.start()
# wait for all thrades to finish
for t in threads_list:
t.join() print(467, cater_dic)
f_name = 'ALL.csv'
f = open(f_name, 'w', encoding='utf-8-sig')
f.write('')
f.closed
f = open(f_name, 'a', encoding='utf-8-sig')
str = 'city, district, name, address, if_in_business_area, if_in_business_area_criterion,catering_kind, average_price, data_from\n'
f.write(str)
## city,district,address,name,catering_kind,average_price,data_from
count_write_rows = 0
for i in cater_dic:
city = i
if city == '城市':
continue
for ii in cater_dic[i]:
district = ii
for iii in cater_dic[i][ii]:
name = iii
for iv in cater_dic[i][ii][iii]:
address = iv
catering_kind = cater_dic[i][ii][iii][iv]['catering_kind']
average_price = cater_dic[i][ii][iii][iv]['average_price']
if_in_business_area = cater_dic[i][ii][iii][iv]['if_in_business_area']
if_in_business_area_criterion = cater_dic[i][ii][iii][iv]['if_in_business_area_criterion']
data_from = cater_dic[i][ii][iii][iv]['data_from']
str = '%s,%s,%s,%s,%s,%s,%s,%s,%s\n' % (
city, district, name, address, if_in_business_area, if_in_business_area_criterion,
catering_kind, average_price, data_from)
f.write(str)
count_write_rows += 1
f.closed
print(count_write_rows) if __name__ == '__main__':
main()
while fo.readline() 少统计了??
# -*- coding: UTF-8 -*- import re
import pprint
import json
import time
import math
import sys
import requests
import threading
from time import ctime, sleep ZHITONGZI_CITY_DIC = {}
f = open('直筒子市_东莞中山.txt', 'r', encoding='utf-8')
ZHITONGZI_CITY_DIC['东莞市'] = []
ZHITONGZI_CITY_DIC['中山市'] = []
c = 0
for i in f:
ii = i.split(';')
for iii in ii:
iv = iii.split('、')
if len(iv) > 2:
c += 1
for v in iv:
if v.find('(') > -1:
v_ = v.split('(')[1]
elif v.find(')') > -1:
v_ = v.split(')')[0]
else:
v_ = v
if c == 1 or c == 2:
ZHITONGZI_CITY_DIC['东莞市'].append(v_)
elif c == 3 or c == 4:
ZHITONGZI_CITY_DIC['中山市'].append(v_)
f.closed def chk_is_coffee(str):
l_ = ['coffee', 'coffe', 'cafe', 'café', 'starbucks', 'caffé']
# 上岛花式铁板烧 日本菜
# 泛太平洋大酒店面馆 其他
l_b = ['咖啡', '星巴克']
# 星巴克
for i in l_:
if str.upper().find(i.upper()) != -1:
return True
for i in l_b:
if str.find(i) != -1:
return True
return False def chk_kfc_mdl(str):
if str.find(u"麦当劳") != -1:
return 1
elif str.find(u"肯德基") != -1 or str.upper().find(u"KFC") != -1:
return 0
else:
return 2 def get_name(str):
if str.find("麦当劳") != -1:
return '麦当劳'
elif str.find("肯德基") != -1 or str.upper().find(u"KFC") != -1:
return '肯德基'
else:
# str = '狗不理包子(前门店)'
# str = '(清真)三羊水饺(新民路店)'
# | 添椒 | 潮涮三国IP火锅
if str.find('(') == -1 and str.find('(') == -1:
return str
res = str.strip(' ').split('(')[0].strip(' ')
if len(res) == 0:
try:
res = str.split(')')[1].split('(')[0]
except Exception:
print(Exception)
# 一锅两头牛(烟青路店)
res_b = res
try:
res_b = res.split('(')[0]
except Exception:
print(Exception) return res_b def chk_city_district(str):
city_district = str.replace(' ', '')
if re.match(r".*[a-zA-Z0-9]", city_district) is not None:
return False
elif str.find("[") != -1 or str.find("(") != -1 or str.find(")") != -1:
return False
else:
return city_district def chk_catering_kind(str):
catering_kind = str.replace(' ', '')
if re.match(r".*[0-9]", catering_kind) is not None:
return False
else:
return catering_kind # ['a','',' ']
def chk_list_thickness(list_):
if len(list_) == 0:
return False
res_list = []
for i in list_:
i_b = i.replace(' ', '')
if i.replace(' ', '') == '':
return False
else:
res_list.append(i_b)
return res_list business_area_tag_list = ['大厦', '大楼', '大厦', '百货', '购物中心', '商业中心', 'MALL', '广场', '商场', '单元', '栋', '座', '楼', '层', '底商'] def chk_in_business_area(str):
global business_area_tag_list
for i in business_area_tag_list:
if str.find(i) > -1:
return 1
return 0 # MAX_OFFSET = 25
# OFFSET = MAX_OFFSET - 1
MAX_PAGINATION = 100
pagination = MAX_PAGINATION
QPS = 50
TIME_UNIT = 1
# http://lbs.amap.com/api/webservice/guide/tools/info
INFOCODE_OK = '10000'
file_name_key_pool = 'key_pool.pool'
KEY_POOL_LIST = []
touse_key = ''
f = open(file_name_key_pool, 'r', encoding='utf-8')
for i in f:
try:
list_ = i.split('\t')
key = i.split('\t')[1].split()
KEY_POOL_LIST.append(key[0])
except Exception:
print(Exception)
KEY_POOL_NUM_INDICATOR = len(KEY_POOL_LIST) - 1 # 北京市 西城区 金堂羊蝎子火锅 真武庙四条1号
# http://restapi.amap.com/v3/place/around?parameters
URL_TYPE = 'http://restapi.amap.com/v3/place/text'
# URL_TYPE = 'http://restapi.amap.com/v3/around'
touse_key = ''
RADIUS = '&radius=20'
keywords = '&keywords='
OFFSET = '&offset=10'
CITYLIMIT = '&citylimit=true' URL_FOR_CHANGE_KEY = 'http://restapi.amap.com/v3/place/text?key=%s&types=060100&city=010&OFFSET=1' def change_key():
global touse_key
for i in range(0, KEY_POOL_NUM_INDICATOR, 1):
key = KEY_POOL_LIST[i]
if key == touse_key:
continue
touse_key = key
url = URL_FOR_CHANGE_KEY % (touse_key)
print(62, 'chk_key', url)
print(62, 'touse_key', touse_key)
try:
r = requests.get(url)
except Exception:
print(Exception)
change_key()
json_ = r.json()
infocode = json_['infocode']
if not infocode == INFOCODE_OK:
if i == KEY_POOL_NUM_INDICATOR:
sys.exit('NOInvalidKEY')
change_key() # 060101 购物服务 商场 购物中心
FILTER_GD_BUSINESS_AREA_TYPE_LIST = ['购物中心'] def fliter_gd_business_area_type(url):
global FILTER_GD_BUSINESS_AREA_TYPE_LIST
# {"suggestion":{"keywords":{},"cities":{}},"info":"OK","status":"1","count":"1","pois":[{"typecode":"050118","adname":"西城区","biz_type":"diner","id":"B0FFG8RYC7","pname":"北京市","importance":{},"location":"116.393715,39.957242","distance":{},"tel":"18600185618","biz_ext":{},"shopid":{},"address":"德胜街道六铺炕北小街8-1号","poiweight":{},"cityname":"北京市","type":"餐饮服务;中餐厅;特色\/地方风味餐厅","shopinfo":"0","name":"炙热青春"}],"infocode":"10000"
try:
r = requests.get(url)
r_json = r.json()
except Exception:
print(Exception)
print(195, url)
return 0
infocode = r_json['infocode']
if infocode == '10000':
count = r_json['count']
if int(count) > 0:
pois_list = r_json['pois']
for l in pois_list:
type = l['type']
for chk_type in FILTER_GD_BUSINESS_AREA_TYPE_LIST:
if type.find(chk_type) > -1:
return 1
else:
change_key()
return 0 # f = open('MEITUAN_DAZHONG_20170704.csv', 'r', encoding='gbk')
# f_2 = open('MEITUAN_DAZHONG_20170705.csv', 'r', encoding='gbk')
# f_gd = open('GD_POI_KFC_MC.csv', 'r', encoding='utf-8-sig') # 市key-区key-品牌名key-地址key-{菜类,均价,data_from}
# {city:{district:{name:{address:{catering_kind,average_price,data_from}}}}}
cater_dic = {}
# [{city,district,address,name,catering_kind,average_price,data_from}]
cater_exception_list = []
count_catering = 0
count_catering_exception = 0 coffee_list = []
count_coffee = 0 fo = open('MEITUAN_DAZHONG_20170705 - 副本.csv', 'r', encoding='gbk') # line = fo.readline()
file_line_list = []
while fo.readline():
file_line_list.append(fo.readline())
file_line_list_len = len(file_line_list)
file_jump_step_num = 5000
count_catering_exception = 0
count_coffee = 0
count_catering = 0 def get_exception_logic_split_loop(nloop):
print(247,nloop)
global touse_key,cater_dic, file_line_list, file_line_list_len, file_jump_step_num, count_catering_exception, count_coffee, count_catering
start_line = nloop * file_jump_step_num
if start_line >= file_line_list_len:
print('last-line')
return
else:
start_line_count = 0
end_line = start_line + file_jump_step_num
if end_line >= file_line_list_len:
end_line = file_line_list_len - 1
for i in range(start_line, end_line, 1):
l_ = file_line_list[i].replace('\n', '').split(',')
city = l_[0]
district = l_[1]
address = l_[2]
name = l_[3]
average_price = l_[4]
catering_kind = l_[5]
data_from = 'mtdz_5'
# 数据准备层
# 数据运算层
# 该层处理从目标文件取出的字段列表
focus_list = [city, district, address, name, catering_kind, average_price, data_from]
dic_exception = {}
dic_exception['data_from'] = data_from
dic_exception['city'] = city
dic_exception['district'] = district
dic_exception['name'] = name
dic_exception['address'] = address
dic_exception['catering_kind'] = catering_kind
dic_exception['average_price'] = average_price if not chk_list_thickness(focus_list) or not chk_city_district(city) or not chk_city_district(
district) or not chk_catering_kind(catering_kind):
count_catering_exception += 1
cater_exception_list.append(dic_exception)
else:
name = get_name(name) m = chk_is_coffee(name)
# if m:
# print(list_)
if not m:
m = chk_is_coffee(catering_kind)
if m:
count_coffee += 1
coffee_list.append(dic_exception) if not m:
dic_details = {}
dic_details['data_from'] = data_from
dic_details['catering_kind'] = catering_kind
dic_details['average_price'] = average_price
if_in_business_area = chk_in_business_area(address)
if_in_business_area_criterion = 'str_match'
if if_in_business_area == 0:
city_r = '&city=' + district
keywords = '&keywords=' + address + '|' + name
start_line_count += 1
print(417, start_line,start_line_count)
if start_line_count%QPS == 0:
print('sleep')
sleep(1)
url = URL_TYPE + '?' + 'key=' + touse_key + RADIUS + keywords + city_r + CITYLIMIT if_in_business_area = fliter_gd_business_area_type(url)
if if_in_business_area == 1:
if_in_business_area_criterion = 'request_api' dic_details['if_in_business_area_criterion'] = if_in_business_area_criterion
dic_details['if_in_business_area'] = if_in_business_area if city not in cater_dic:
cater_dic[city] = {}
if district not in cater_dic[city]:
cater_dic[city][district] = {}
if name not in cater_dic[city][district]:
cater_dic[city][district][name] = {}
if address not in cater_dic[city][district][name]:
cater_dic[city][district][name][address] = {} cater_dic[city][district][name][address] = dic_details
count_catering += 1 class MyThread(threading.Thread):
def __init__(self,func,args,name=''):
threading.Thread.__init__(self)
self.name = name
self.func = func
self.args = args
def run(self):
self.func(self.args) def main():
print('starting at:',ctime())
threads_list = []
thread_sum = math.floor(file_line_list_len / file_jump_step_num)
print(thread_sum)
for nloop in range(1, thread_sum, 1):
print(nloop)
thread_instance = MyThread(get_exception_logic_split_loop,(nloop),get_exception_logic_split_loop.__name__)
print(353,'123')
threads_list.append(thread_instance)
# 主进程将在所有非守护进程退出后,退出
for t in threads_list:
print(t)
t.setDaemon = False
t.start()
# wait for all thrades to finish
for t in threads_list:
t.join() print(467, cater_dic)
f_name = 'ALL.csv'
f = open(f_name, 'w', encoding='utf-8-sig')
f.write('')
f.closed
f = open(f_name, 'a', encoding='utf-8-sig')
str = '市,区,品牌名,地址,是否在商场,菜别(类型),均价,data_from,\n'
f.write(str)
## city,district,address,name,catering_kind,average_price,data_from
count_write_rows = 0
for i in cater_dic:
city = i
if city == '城市':
continue
for ii in cater_dic[i]:
district = ii
for iii in cater_dic[i][ii]:
name = iii
for iv in cater_dic[i][ii][iii]:
address = iv
catering_kind = cater_dic[i][ii][iii][iv]['catering_kind']
average_price = cater_dic[i][ii][iii][iv]['average_price']
if_in_business_area = cater_dic[i][ii][iii][iv]['if_in_business_area']
if_in_business_area_criterion = cater_dic[i][ii][iii][iv]['if_in_business_area_criterion']
data_from = cater_dic[i][ii][iii][iv]['data_from']
str = '%s,%s,%s,%s,%s,%s,%s,%s,%s\n' % (
city, district, name, address, if_in_business_area, if_in_business_area_criterion,
catering_kind, average_price, data_from)
f.write(str)
count_write_rows += 1
f.closed
print(count_write_rows) if __name__ == '__main__':
main()
thread_process_action的更多相关文章
随机推荐
- 简述移动端与PC端的区别
1.移动端与PC端的区别 PC考虑的是浏览器的兼容性,而移动端开发考虑的更多的是手机兼容性,因为目前不管是android手机还是ios手机,一般浏览器使用的都是webkit内核,所以说做移动端开发,更 ...
- python基础-2 编码转换 pycharm 配置 运算符 基本数据类型int str list tupple dict for循环 enumerate序列方法 range和xrange
1.编码转换 unicode 可以编译成 UTF-U GBK 即 #!/usr/bin/env python # -*- coding:utf-8 -*- a = '测试字符' #默认是utf-8 a ...
- SpringBoot 使用maven创建springboot项目
有两种方式可以创建 1是使用spring-boot-starter-parent ,2是使用spring-boot-dependencies (即父项目dependencyManagement) ( ...
- 多线程10-SemaphoreSlim
); ;i<=;i++) { + * i; )); C ...
- [Git] 012 rm 命令的补充
0. 前言 [Git] 007 三棵树以及向本地仓库加入第一个文件 的 "2.5" 有提及 git rm --cached <file> 1. 介绍 git rm &l ...
- jsp自定义标签处理转义字符
sun公司提供的jstl虽然比较强大,但是开发中很难满足我们所有的需求,并且开发也禁止在jsp中写很多java代码,因此很多场景需要自己定义标签进行项目开发 sun提供的标签库引用方式:<%@t ...
- Eclipse- 使用记录(1)
1.快捷键篇 (1)常用的快捷键: 1>ctrl+shift+R:查找源 2>ctrl+shift+G:查找引用 3>alt+Enter:查看某文件或文件夹的Properties ( ...
- hdu-1045.fire net(缩点 + 二分匹配)
Fire Net Time Limit: 2000/1000 MS (Java/Others) Memory Limit: 65536/32768 K (Java/Others)Total Su ...
- windows 端 nginx怎么配置 虚拟机的fastdfs文件管理系统
FastDFS的安装这里不演示 nginx.conf #图片服务 upstream img_server_pool{ server 192.168.133.131:80 weight=10; } #学 ...
- 从零开始学编程_第A001期_C语言HelloWorld详解
emmm,这是我的第一篇博客. 作为一个软件工程专业的学生,我希望自己能在编程方面有不错的成就,我们老师告诉我们学编程就要写博客,在写博客的过程中不断成长,结交朋友,所以我就开始尝试写专业相关的博客. ...