[Python爬虫] 之三十：Selenium +phantomjs 利用 pyquery抓取栏目
一、介绍
本例子用Selenium +phantomjs爬取栏目（http://tv.cctv.com/lm/）的信息
二、网站信息
三、数据抓取
首先抓取所有要抓取网页链接，共39页，保存到数据库里面
def getUrls(self):
urls = []
urls.append('http://tv.cctv.com/lm/')
for index in range(2,40):
urls.append("javascript:window.scroll(0,145);DataInteraction({0});showPageTitle_fenyei2('ELMT1413526954890942',{0});".format(index))
self.db.SaveCCTVColumnUrls(urls,'')
针对上面的网站信息，来进行抓取
1、首先抓取信息列表
抓取代码：Elements = doc("div[id='text_box_0']").find('dl').find('dd')
2、栏目名称，链接
column1Element = element.find('div[class="text"]').find('h3').find('a')
columnName = column1Element.text().encode('utf8').replace(',', '，').replace('\n', '')
columnUrl = column1Element.attr('href')
四，实现代码
# coding=utf-8
import os
import re
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from datetime import datetime,timedelta
import selenium.webdriver.support.ui as ui
import time
from pyquery import PyQuery as pq
import columnData
import mongoDB
class cctvColumnInfo: def __init__(self):
#通过配置文件获取IEDriverServer.exe路径
# self.urls = self.getUrls()
# IEDriverServer ='C:\Program Files\Internet Explorer\IEDriverServer.exe'
# self.driver = webdriver.Ie(IEDriverServer)
# self.driver.maximize_window()
self.driver = webdriver.PhantomJS(service_args=['--load-images=false'])#service_args=['--load-images=false']
self.driver.set_page_load_timeout(10)
self.driver.maximize_window()
self.db = mongoDB.mongoDbBase() def WriteUrl(self,url):
fileName = os.path.join(os.getcwd(), 'cctvColumn/cctvColumn_url.txt')
with open(fileName, 'a') as f:
f.write('\n'+url) def getUrls(self):
urls = []
urls.append('http://tv.cctv.com/lm/')
for index in range(2,40):
urls.append("javascript:window.scroll(0,145);DataInteraction({0});showPageTitle_fenyei2('ELMT1413526954890942',{0});".format(index))
self.db.SaveCCTVColumnUrls(urls,'')
# return urls def WriteLog(self, message,date):
fileName = os.path.join(os.getcwd(), 'cctvColumn/cctvColumn-'+date + '.txt')
with open(fileName, 'a') as f:
f.write(message) def getColumnInfo(self, colInfo):
ts = colInfo.split('主持人')
firstBroadcastTime = ts[0]
ts1 = ts[1].split('播出频道')
columnHost = '主持人' + ts1[0]
broadcastChannel = '播出频道' + ts1[1]
return firstBroadcastTime, columnHost, broadcastChannel def CatchData(self): urlIndex = 0
urls = self.db.GetCCTVColumnUrls()
itemIndex = 0
for u in urls:
url = u['url']
try:
if url == 'http://tv.cctv.com/lm/':
self.driver.get(url)
else:
self.driver.execute_script(url)
urlIndex += 1
time.sleep(2)
selenium_html = self.driver.execute_script("return document.documentElement.outerHTML")
doc = pq(selenium_html)
# Elements = doc("div[@id='text_box_0']/dl/dd")
Elements = doc("div[id='text_box_0']").find('dl').find('dd')
message = '' # for element in Elements:
column_name = url.encode('utf8')
print url
for element in Elements.items():
colobj = columnData.columnData()
itemIndex+=1
firstBroadcastTime = ''
ReplayBroadcastTime = ''
firstBroadcastChannel = ''
# column1Element = element.find('div[@class="text"]/h3/a')
# column1Element = element.find_element_by_xpath("//div[@class='ui-page-next']")
column1Element = element.find('div[class="text"]').find('h3').find('a')
columnName = column1Element.text().encode('utf8').replace(',', '，').replace('\n', '')
columnUrl = column1Element.attr('href') colobj.setColumnName(columnName)
colobj.setColumnUrl(columnUrl)
column_name += '\n' + columnName
# time.sleep(3)
print columnName # column2Element = element.find('div[@class="text"]/p/a')
column2Element = element.find('div[class="text"]').find('p').find('a')
columnTimeName = column2Element.text().encode('utf8').replace(',', '，').replace('\n', '')
columnTimeUrl = column2Element.attr('href')
colobj.setColumnTimeName(columnTimeName)
colobj.setColumnTimeUrl(columnTimeUrl)
# print columnTimeName + '; ' + columnTimeUrl # column34Elements = element.find('div[@class="text"]/span/a')
column34Elements = element.find('div[class="text"]').find('span').find('a') # for column34Element in column34Elements:
column34Index = 0
pastVideoUrl = ''
officialWebsiteUrl = ''
for column34Element in column34Elements.items():
if column34Index == 0:
pastVideoUrl = column34Element.attr('href')
colobj.setPastVideoUrl(pastVideoUrl)
else:
officialWebsiteUrl = column34Element.attr('href')
colobj.setOfficialWebsiteUrl(officialWebsiteUrl)
column34Index += 1 # columnImageElement = element.find('div[@class="img"]/a/img')
columnImageElement = element.find('div[class="img"]').find('a').find('img')
colImgUrl = columnImageElement.attr('src') if colImgUrl == None:
columnImageElement = element.find('div[class="image"]').find('a').find('img')
colImgUrl = columnImageElement.attr('src')
# print colImgUrl
colobj.setColImgUrl(colImgUrl)
# 首播时间
firstBroadcastTime1 = ''
# 主持人
columnHost = ''
# 播出频道
firstBroadcastChannel1 =''
# columnInfos = element.find('div[@class="lr"]/div')
columnInfos = element.find('div[class="lr"]').find('div')
if columnInfos:
for colInfo in columnInfos.items():
firstBroadcastTime1, columnHost, firstBroadcastChannel1 = self.getColumnInfo(
colInfo.text().encode('utf8').replace(',', '，').replace('\n', ''))
columnHost = columnHost.replace(',', '，')
if not firstBroadcastTime:
firstBroadcastTime = firstBroadcastTime1
if not firstBroadcastChannel:
firstBroadcastChannel = firstBroadcastChannel1
colobj.setColumnHost(columnHost)
colobj.setFirstBroadcastChannel(firstBroadcastChannel1)
colobj.setFirstBroadcastTime(firstBroadcastTime1)
# 栏目名称，首播时间，重播时间，播出频道，主持人，栏目url,栏目名称1(带时间的）,栏目名称1url,往期视频url,栏目官网url,），栏目对应图片url
mess = '\n{0},{1},{2},{3},{4},{5},{6},{7},{8},{9},{10}'.format(columnName, firstBroadcastTime,
ReplayBroadcastTime,
firstBroadcastChannel, columnHost,
columnUrl, columnTimeName,
columnTimeUrl, pastVideoUrl,
officialWebsiteUrl, colImgUrl) # print mess
message += mess self.db.SaveCCTVColumnData(colobj,itemIndex)
self.db.SaveCCTVColumnUrl(columnUrl, '', columnName) date = time.strftime('%Y-%m-%d')
self.WriteLog(message, date)
self.WriteUrl(column_name)
self.db.SetCCTVColumnUrlCrawlState(url)
except TimeoutException,e:
print 'timeout url: '+url self.driver.close()
self.driver.quit() def getBroadCast(self):
urls = self.db.GetSubCCTVColumnUrls() for u in urls:
firstBroadcastTime = ''
ReplayBroadcastTime = ''
firstBroadcastChannel = ''
messsage = ''
url = u['url']
# url='http://tv.cctv.com/lm/xqds'
# url='http://tv.cctv.com/lm/24xiaoshi/'
columnName = u['columnName'] # u'http://tv.cctv.com/lm/kanjian'
try:
self.driver.get(url)
time.sleep(2)
selenium_html = self.driver.execute_script("return document.documentElement.outerHTML")
doc = pq(selenium_html)
Elements = doc("p[class='p_1']") index = 0
for element in Elements.items():
if index == 0:
firstBroadcastTime = element.text().encode('utf8').replace(',', '，').replace('\n', '')
elif index == 1:
ReplayBroadcastTime = element.text().encode('utf8').replace(',', '，').replace('\n', '')
elif index == 2:
firstBroadcastChannel = element.text().encode('utf8').replace(',', '，').replace('\n', '')
break
index += 1
if index == 0:
Elements = doc("div[class='head_msg']").find('table').find('tbody').find('tr') for element in Elements.items():
messsage+=element.text().encode('utf8').replace(',', '，').replace('\n', '') if messsage:
firstBroadcastTime, ReplayBroadcastTime, firstBroadcastChannel= self.getBroadInfo(columnName.encode('utf8'),messsage)
self.db.SetCCTVColumnUrlCrawlState(url) if firstBroadcastChannel:
colobj = columnData.columnData()
colobj.setColumnName(columnName)
colobj.setFirstBroadcastTime(firstBroadcastTime)
colobj.setFirstBroadcastChannel(firstBroadcastChannel)
colobj.setReplayBroadcastTime(ReplayBroadcastTime)
self.db.UpdateCCTVColumnData(colobj)
print '\n'
print url
print columnName
print firstBroadcastTime
print firstBroadcastChannel
print ReplayBroadcastTime except TimeoutException, e:
print 'TimeoutException:'+url def getBroadInfo(self,columnName,column):
# column ='首播频道： CCTV-14首播时间： 周三17:15'
firstBroadcastTime = ''
ReplayBroadcastTime = ''
firstBroadcastChannel = ''
column=column.replace('栏目大全','')
if '>>' in column:
index = column.index('>>')
column = column[0:index] if 'CCTV13' in column:
column = column.replace('CCTV13', 'CCTV-13')
if 'CCTV6' in column:
column = column.replace('CCTV6', 'CCTV-6')
if 'CCTV1' in column:
column = column.replace('CCTV1','CCTV-1') if '官方微信' in column:
index = column.index('官方微信')
column = column[0:index] # if '停播' in column or '关闭' in column:
# return firstBroadcastTime, ReplayBroadcastTime, firstBroadcastChannel
# elif '>>' in column:
# index = column.index('>>')
# column = column[0:index] if '首播时间' in column:
if '重播时间' in column:
cols = column.split('重播时间')
firstBroadcastTime = cols[0]
if '独播频道' in cols[1]:
ReplayBroadcastTime = '重播时间' + cols[1].split('独播频道')[0]
firstBroadcastChannel = '独播频道' + cols[1].split('独播频道')[1]
elif '首播频道' in cols[1]:
ReplayBroadcastTime = '重播时间' + cols[1].split('首播频道')[0]
firstBroadcastChannel = '首播频道' + cols[1].split('首播频道')[1] elif '播出频道' in cols[1]:
ReplayBroadcastTime = '重播时间' + cols[1].split('播出频道')[0]
firstBroadcastChannel = '播出频道' + cols[1].split('播出频道')[1]
elif '独播频道' in column:
cols = column.split('独播频道')
firstBroadcastTime = cols[0]
firstBroadcastChannel = '独播频道' + cols[1]
elif '播出频道' in column:
cols = column.split('播出频道')
firstBroadcastTime = cols[0]
firstBroadcastChannel = '播出频道' + cols[1] elif '首播频道' in column:
cols = column.split('首播频道')
index = column.index('首播频道')
if index==0:
cols = column.split('首播时间')
firstBroadcastChannel = cols[0]
firstBroadcastTime = '首播时间' + cols[1]
else:
firstBroadcastTime = cols[0]
firstBroadcastChannel = '首播频道' + cols[1]
else:
if '首播(' in column and '重播(' in column:
if '独播频道' in column:
cols = column.split('独播频道')
firstBroadcastChannel = '独播频道' + cols[1]
firstBroadcastTime = cols[0]
# '首播(生活): 一-六18:52 日18:42重播(生活): 一-五 日16:08首播(文史): 一-五22:43六日22:33/30重播(文史): 二-五06:46六日06:24'
if '（生活版）' in columnName:
if '首播(文史)' in firstBroadcastTime:
temp = firstBroadcastTime.split('首播(文史)')[0]
if '重播(生活)' in temp:
firstBroadcastTime = '首播时间： '+temp.split('重播(生活)')[0].replace('首播(生活): ','')
ReplayBroadcastTime = '重播时间： '+temp.split('重播(生活)')[1].replace(': ','') # 首播(文史): 一-五22:43六日22:33/30重播(文史): 二-五06:46六日06:24首播(生活): 一-六18:52 日18:42重播(生活): 一-五 日16:08
elif '（文史版）' in columnName:
if '首播(生活)' in firstBroadcastTime:
temp = firstBroadcastTime.split('首播(生活)')[0]
if '重播(文史)' in temp:
firstBroadcastTime = '首播时间： '+temp.split('重播(文史)')[0].replace('首播(文史): ','')
ReplayBroadcastTime = '重播时间： '+ temp.split('重播(文史)')[1].replace(': ','') elif '播出频道' in column:
cols = column.split('播出频道')
firstBroadcastTime = cols[0]
firstBroadcastChannel = '播出频道' + cols[1] elif '首播频道' in column:
cols = column.split('首播频道')
firstBroadcastTime = cols[0]
firstBroadcastChannel = '首播频道' + cols[1]
return firstBroadcastTime,ReplayBroadcastTime,firstBroadcastChannel def exportColumnInfo(self):
columns = self.db.GetCCTVColumnData() for col in columns:
columnName = col['columnName'].encode('utf8')
firstBroadcastTime = col['firstBroadcastTime'].encode('utf8')
firstBroadcastTime=firstBroadcastTime.replace('首播时间： ','') firstBroadcastChannel = col['firstBroadcastChannel'].encode('utf8').replace("播出频道：", "").replace("独播频道：", "").replace("首播频道：", "")
firstBroadcastChannel =firstBroadcastChannel.replace(")","").replace("(","").replace("CCTV-8电视剧","CCTV-8 电视剧")
firstBroadcastChannel = firstBroadcastChannel.replace("CCTV-1综合频道", "CCTV-1 综合频道")
firstBroadcastChannel = firstBroadcastChannel.replace("CCTV-1高清频道", "CCTV-1 高清频道")
firstBroadcastChannel = firstBroadcastChannel.replace("CCTV13", "CCTV-13")
firstBroadcastChannel = firstBroadcastChannel.replace("CCTV1", "CCTV-1")
firstBroadcastChannel = firstBroadcastChannel.replace("CCTV-少儿", "CCTV-14 少儿")
firstBroadcastChannel = firstBroadcastChannel.replace("CCTV6", "CCTV-6")
firstBroadcastChannel = firstBroadcastChannel.replace("CCTV-12社会与法", "CCTV-12 社会与法") replayBroadcastTime = col['replayBroadcastTime'].encode('utf8')
replayBroadcastTime = replayBroadcastTime.replace('重播时间：', '')
columnHost = col['columnHost'].encode('utf8')
columnUrl = col['columnUrl'].encode('utf8')
columnTimeName = col['columnTimeName'].encode('utf8')
columnTimeUrl = col['columnTimeUrl']
if columnTimeUrl:
columnTimeUrl = columnTimeUrl.encode('utf8')
officialWebsiteUrl = col['officialWebsiteUrl'].encode('utf8')
pastVideoUrl = col['pastVideoUrl'].encode('utf8')
colImgUrl = col['colImgUrl'].encode('utf8') # 栏目名称，首播时间，重播时间，播出频道，主持人，栏目url,栏目名称1(带时间的）,栏目名称1url,往期视频url,栏目官网url,），栏目对应图片url
message = '\n{0},{1},{2},{3},{4},{5},{6},{7},{8},{9},{10}'.format(columnName, firstBroadcastTime,
replayBroadcastTime,
firstBroadcastChannel, columnHost,
columnUrl, columnTimeName,
columnTimeUrl, pastVideoUrl,
officialWebsiteUrl, colImgUrl) date = time.strftime('%Y-%m-%d')
self.WriteLog(message, date) obj = cctvColumnInfo()
# obj.getUrls()
# obj.CatchData()
# obj.getBroadCast()
obj.exportColumnInfo()
# coding=utf-8
import os
from pymongo import MongoClient
from pymongo import ASCENDING, DESCENDING
import codecs
import time
import columnData
import datetime
import re class mongoDbBase:
# def __init__(self, databaseIp = '127.0.0.1',databasePort = 27017,user = "ott",password= "ott", mongodbName='OTT_DB'):
def __init__(self, connstr='mongodb://ott:ott@127.0.0.1:27017/', mongodbName='OTT'):
# client = MongoClient(connstr)
# self.db = client[mongodbName]
client = MongoClient('127.0.0.1', 27017)
self.db = client.OTT
self.db.authenticate('ott', 'ott') def SaveCCTVColumnData(self,columnData,index):
count = self.db.column_data.find({'columnName': columnData.getColumnName()}).count()
if count == 0:
dictM ={'columnName':columnData.getColumnName(),
'firstBroadcastTime':columnData.getFirstBroadcastTime(),
'replayBroadcastTime':'',
'firstBroadcastChannel':columnData.getFirstBroadcastChannel(),
'columnHost':columnData.getColumnHost(),
'columnUrl':columnData.getColumnUrl(),
'columnTimeName':columnData.getColumnTimeName(),
'columnTimeUrl':columnData.getColumnTimeUrl(),
'officialWebsiteUrl':columnData.getOfficialWebsiteUrl(),
'pastVideoUrl': columnData.getPastVideoUrl(),
'colImgUrl':columnData.getColImgUrl(),
'index':index}
self.db.column_data.insert(dictM) def GetCCTVColumnData(self):
columns = self.db.column_data.find({},{'_id':0})
return columns def UpdateCCTVColumnData(self, columnData):
dictM ={'$set':{'replayBroadcastTime':columnData.getReplayBroadcastTime(),
'firstBroadcastTime':columnData.getFirstBroadcastTime(),
'firstBroadcastChannel': columnData.getFirstBroadcastChannel()}}
self.db.column_data.update({"columnName":columnData.getColumnName()},dictM) def SaveCCTVColumnUrl(self, url,suburl,columnName):
dictM = {'url': url, 'iscrawl': '','suburl':suburl,'columnName':columnName}
# db.urls.find({iscrawl:'1'}).count()
count = self.db.columnurls.find({'url': url}).count()
if count == 0:
self.db.columnurls.insert(dictM) def SaveCCTVColumnUrls(self, urlList,suburl):
index = 0
for url in urlList: # db.urls.find({iscrawl:'1'}).count()
count = self.db.columnurls.find({'url': url}).count()
if count == 0:
dictM = {'url': url, 'iscrawl': '', 'suburl': suburl,'index':index}
self.db.columnurls.insert(dictM)
index += 1
# self.db.Meeting.update({'title': meet["title"],'date': meet["date"]}, {'$set': dictM}, {'upsert': True}) def GetCCTVColumnUrls(self):
urls = self.db.columnurls.find({'iscrawl': '','suburl':''}, {'_id': 0, 'url': 1})
# for url in urls:
# #http://top.chinaz.com/hangye/index_yule.html
# print urls['url']
# break
return urls def GetSubCCTVColumnUrls(self):
urls = self.db.columnurls.find({'iscrawl': '', 'suburl': ''}, {'_id': 0, 'url': 1,'columnName':1})
# urls = self.db.columnurls.find({'firstBroadcastChannel': re.compile('栏目'), 'suburl': '1'}, {'_id': 0, 'url': 1, 'columnName': 1})
return urls
# def SetUrlCrawlState(self,urlList):
# for url in urlList:
# self.db.urls.update({'url':url},{'$set':{'iscrawl':'1'}}) def SetCCTVColumnUrlCrawlState(self, url):
# db.urls.update({iscrawl:'1'},{'$set':{iscrawl:'0'}},false,true)
self.db.columnurls.update({'url': url}, {'$set': {'iscrawl': ''}}) # d = mongoDbBase() # urls = []
# urls.append('abc')
# # d.SaveUrls(urls)
# d.SetUrlCrawlState(urls)
def download(self, url, name):
try:
# url='http://pp.myapp.com/ma_icon/0/icon_10910_1523714409/96'
# name='D:\work\python_crawl\down\2019.jpg'
pic = requests.get(url, timeout=5)
with open(name, 'wb') as f:
f.write(pic.content)
except requests.exceptions.ConnectionError:
print('当前图片无法下载')
[Python爬虫] 之三十：Selenium +phantomjs 利用 pyquery抓取栏目的更多相关文章
- [Python爬虫] 之三十一：Selenium +phantomjs 利用 pyquery抓取消费主张信息
一.介绍 本例子用Selenium +phantomjs爬取央视栏目(http://search.cctv.com/search.php?qtext=消费主张&type=video)的信息(标 ...
- [Python爬虫] 之十六：Selenium +phantomjs 利用 pyquery抓取一点咨询数据
本篇主要是利用 pyquery来定位抓取数据,而不用xpath,通过和xpath比较,pyquery效率要高. 主要代码: # coding=utf-8 import os import re fro ...
- [Python爬虫] 之二十五：Selenium +phantomjs 利用 pyquery抓取今日头条网数据
一.介绍 本例子用Selenium +phantomjs爬取今日头条(http://www.toutiao.com/search/?keyword=电视)的资讯信息,输入给定关键字抓取资讯信息. 给定 ...
- [Python爬虫] 之二十二：Selenium +phantomjs 利用 pyquery抓取界面网站数据
一.介绍 本例子用Selenium +phantomjs爬取界面(https://a.jiemian.com/index.php?m=search&a=index&type=news& ...
- [Python爬虫] 之二十九：Selenium +phantomjs 利用 pyquery抓取节目信息信息
一.介绍 本例子用Selenium +phantomjs爬取节目(http://tv.cctv.com/epg/index.shtml?date=2018-03-25)的信息 二.网站信息 三.数据抓 ...
- [Python爬虫] 之二十八：Selenium +phantomjs 利用 pyquery抓取网站排名信息
一.介绍 本例子用Selenium +phantomjs爬取中文网站总排名(http://top.chinaz.com/all/index.html,http://top.chinaz.com/han ...
- [Python爬虫] 之二十四：Selenium +phantomjs 利用 pyquery抓取中广互联网数据
一.介绍 本例子用Selenium +phantomjs爬取中广互联网(http://www.tvoao.com/select.html)的资讯信息,输入给定关键字抓取资讯信息. 给定关键字:数字:融 ...
- [Python爬虫] 之十九：Selenium +phantomjs 利用 pyquery抓取超级TV网数据
一.介绍 本例子用Selenium +phantomjs爬取超级TV(http://www.chaojitv.com/news/index.html)的资讯信息,输入给定关键字抓取资讯信息. 给定关键 ...
- [Python爬虫] 之十八：Selenium +phantomjs 利用 pyquery抓取电视之家网数据
一.介绍 本例子用Selenium +phantomjs爬取电视之家(http://www.tvhome.com/news/)的资讯信息,输入给定关键字抓取资讯信息. 给定关键字:数字:融合:电视 抓 ...
随机推荐
- Mysql 中的Text字段的范围
mysql中text 最大长度为65,535(2的16次方–1)字符的TEXT列.如果你觉得text长度不够,可以选择 MEDIUMTEXT最大长度为16,777,215. LONGTEXT最大长度为 ...
- 邂逅Sass和Compass之Sass篇
对于一个从后台转到前端的web开发者来说,最大的麻烦就是写CSS,了解CSS的人都知道,它可以开发网页样式,但是没法用它编程,感觉耦合性相当的高,如果想要方便以后维护,只能逐句修改甚至重写相当一部分的 ...
- netcore 配置文件使用
一直在记录整理接口调用,但是最近发现关于项目在vs中本地启动也有许多方便的地方. 首先由于使用的是Java的Eureka和网关来做的服务基础, 然后服务就涉及到注册一说, 问题是,如果appsetti ...
- jquery扩展插件，让demo元素也可以resize
(function($, h, c) { var a = $([]), e = $.resize = $.extend($.resize, {}), i, k = "setTimeout&q ...
- 【笔试题】Spring笔试题
spring笔试题 1.Spring支持的事务管理类型 Spring支持两种类型的事务管理: 编程式事务管理:这意味你通过编程的方式管理事务,给你带来极大的灵活性,但是难维护. 声明式事务管理:这意味 ...
- windows 安装tp5 composer方式
1.下载windows composer-setup.exe(我已下载一个Composer-Setup.exe); 2.我电脑使用的是phpstudy2018版 php-7.0.12-NTS 3.然后 ...
- 如何直接运行python文件
1. 在Windows上是不能直接运行python文件的,但是,在Mac和Linux上是可以的,方法是在.py文件的第一行加上一个特殊的注释: #!/usr/bin/env python3 print ...
- 字典树&01字典树算法笔记
1]学习了字典树之后,觉得它很明显的就是用空间来换时间,空间复杂度特别大,比如字典数单单存26个小写字母,那么每个节点的孩子节点都有26个孩子节点,字典树中的每一层都保留着不同单词的相同字母. 2]0 ...
- JZYZOJ1454 NOIP2015 D2T3_运输计划 二分 差分数组 lca tarjan 树链剖分
http://172.20.6.3/Problem_Show.asp?id=1454 从这道题我充分认识到我的脑子里好多水orz. 如果知道了这个要用二分和差分写,就没什么思考上的难点了(屁咧你写了一 ...
- 14年安徽省赛数论题etc.
关于最大公约数的疑惑 题目描述 小光是个十分喜欢素数的人,有一天他在学习最大公约数的时候突然想到了一个问题,他想知道从1到n这n个整数中有多少对最大公约数为素数的(x,y),即有多少(x,y),gcd ...