【scrapy实践】_爬取安居客_广州_新楼盘数据

需求：爬取【安居客—广州—新楼盘】的数据，具体到每个楼盘的详情页的若干字段。

难点：楼盘类型各式各样：住宅 别墅 商住 商铺 写字楼，不同楼盘字段的名称不一样。然后同一种类型，比如住宅，又分为不同的情况，比如分为期房在售，现房在售，待售，尾盘。其他类型也有类似情况。所以字段不能设置固定住。

解决方案：目前想到的解决方案，第一种：scrapy中items.py中不设置字段，spider中爬的时候自动识别字段（也就是有啥字段就保留下来），然后返回字典存起来。第二种，不同字段的网页分别写规则单独抓取。显然不可取。我采用的是第一种方案。还有其他方案的朋友们，欢迎交流哈。

目标网址为：http://gz.fang.anjuke.com/ 该网页下的楼盘数据

示例楼盘网址：http://gz.fang.anjuke.com/loupan/canshu-298205.html?from=loupan_tab

开始编写scrapy脚本。建立工程步骤略过。

1、count.py

 __author__ = 'Oscar_Yang'
 #-*- coding= utf-8 -*-
 """
     查看mongodb存储状况的脚本count.py
 """
 import time
 import pymongo
 client = pymongo.MongoClient("localhost", 27017)
 db = client["SCRAPY_anjuke_gz"]
 sheet = db["anjuke_doc1"]

 while True:
     print(sheet.find().count())
     print("____________________________________")
     time.sleep(3)

 """
     entrypoint.py
 """
 from scrapy.cmdline import execute
 execute(['scrapy', 'crawl', 'anjuke_gz'])

 # -*- coding: utf-8 -*-
 """
     settings.py
 """

 # Scrapy settings for anjuke_gz project
 #
 # For simplicity, this file contains only settings considered important or
 # commonly used. You can find more settings consulting the documentation:
 #
 #     http://doc.scrapy.org/en/latest/topics/settings.html
 #     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
 #     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

 BOT_NAME = 'anjuke_gz'

 SPIDER_MODULES = ['anjuke_gz.spiders']
 NEWSPIDER_MODULE = 'anjuke_gz.spiders'
 MONGODB_HOST = "127.0.0.1"
 MONGODB_PORT = 27017
 MONGODB_DBNAME="SCRAPY_anjuke_gz"
 MONGODB_DOCNAME="anjuke_doc1"

 # Crawl responsibly by identifying yourself (and your website) on the user-agent
 #USER_AGENT = 'anjuke_gz (+http://www.yourdomain.com)'

 # Obey robots.txt rules
 ROBOTSTXT_OBEY = False

 # Configure maximum concurrent requests performed by Scrapy (default: 16)
 #CONCURRENT_REQUESTS = 32

 # Configure a delay for requests for the same website (default: 0)
 # See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
 # See also autothrottle settings and docs
 #DOWNLOAD_DELAY = 3
 # The download delay setting will honor only one of:
 #CONCURRENT_REQUESTS_PER_DOMAIN = 16
 #CONCURRENT_REQUESTS_PER_IP = 16

 # Disable cookies (enabled by default)
 #COOKIES_ENABLED = False

 # Disable Telnet Console (enabled by default)
 #TELNETCONSOLE_ENABLED = False

 # Override the default request headers:
 #DEFAULT_REQUEST_HEADERS = {
 #   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
 #   'Accept-Language': 'en',
 #}

 # Enable or disable spider middlewares
 # See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
 #SPIDER_MIDDLEWARES = {
 #    'anjuke_gz.middlewares.AnjukeGzSpiderMiddleware': 543,
 #}

 # Enable or disable downloader middlewares
 # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
 #DOWNLOADER_MIDDLEWARES = {
 #    'anjuke_gz.middlewares.MyCustomDownloaderMiddleware': 543,
 #}

 # Enable or disable extensions
 # See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
 #EXTENSIONS = {
 #    'scrapy.extensions.telnet.TelnetConsole': None,
 #}

 # Configure item pipelines
 # See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
 ITEM_PIPELINES = {
    'anjuke_gz.pipelines.AnjukeGzPipeline': 300,
 }

 # Enable and configure the AutoThrottle extension (disabled by default)
 # See http://doc.scrapy.org/en/latest/topics/autothrottle.html
 #AUTOTHROTTLE_ENABLED = True
 # The initial download delay
 #AUTOTHROTTLE_START_DELAY = 5
 # The maximum download delay to be set in case of high latencies
 #AUTOTHROTTLE_MAX_DELAY = 60
 # The average number of requests Scrapy should be sending in parallel to
 # each remote server
 #AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
 # Enable showing throttling stats for every response received:
 #AUTOTHROTTLE_DEBUG = False

 # Enable and configure HTTP caching (disabled by default)
 # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
 HTTPCACHE_ENABLED = True
 HTTPCACHE_EXPIRATION_SECS = 0
 HTTPCACHE_DIR = 'httpcache'
 HTTPCACHE_IGNORE_HTTP_CODES = []
 HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

接下来，是items。因为没有设置字段，为默认的代码。

 # -*- coding: utf-8 -*-

 # Define here the models for your scraped items
 #
 # See documentation in:
 # http://doc.scrapy.org/en/latest/topics/items.html

 import scrapy

 class AnjukeGzItem(scrapy.Item):
     # define the fields for your item here like:
     # name = scrapy.Field()
     pass

接下来，是piplines.py。在中设置了mongodb的配置。

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html

import pymongo
from scrapy.conf import settings

class AnjukeGzPipeline(object):
    def __init__(self):
        host=settings["MONGODB_HOST"]
        port=settings["MONGODB_PORT"]
        dbname=settings["MONGODB_DBNAME"]
        client=pymongo.MongoClient(port=port,host=host)
        tdb = client[dbname]
        self.post=tdb[settings["MONGODB_DOCNAME"]]
    def process_item(self,item,spider):
        info = dict(item)
        self.post.insert(info)
        return item

最后，是最主要的spider.py

 from scrapy.http import Request
 import scrapy
 from bs4 import BeautifulSoup
 import re
 import requests
 """
     spider脚本
 """
 class Myspider(scrapy.Spider):
     name = 'anjuke_gz'
     allowed_domains = ['http://gz.fang.anjuke.com/loupan/']
     start_urls = ["http://gz.fang.anjuke.com/loupan/all/p{}/".format(i) for i in range(39)]

     def parse(self, response):
         soup = BeautifulSoup(response.text,"lxml")
         content=soup.find_all(class_="items-name") #返回每个楼盘的对应数据
         for item in content:
             code=item["href"].split("/")[-1][:6]
             real_href="http://gz.fang.anjuke.com/loupan/canshu-{}.html?from=loupan_tab".format(code) #拼凑出楼盘详情页的url
             res=requests.get(real_href)
             soup = BeautifulSoup(res.text,"lxml")
             a = re.findall(r'<div class="name">(.*?)</div>', str(soup))
             b = soup.find_all(class_="des")
             data = {}
             for (i, j) in zip(range(len(b)), a):
                 data[j] = b[i].text.strip().strip("\t")
                 data["url"] = real_href
             yield data

下面是存入mongodb的情况。

　　因为针对不同的网页结构，爬取的规则是一个，所以爬取的时候就不能针对每个字段进行爬取，所以存到库里的数据如果要是分析的话还需要清洗。

在python中使用mongodb的查询语句，再配合使用pandas应该就很方便清洗了。