爬取IT之家业界新闻

爬取站点  https://it.ithome.com/ityejie/ ，进入详情页提取内容。

  1 import requests
  2 import json
  3 from lxml import etree
  4 from pymongo import MongoClient
  5
  6 url = ‘https://it.ithome.com/ithome/getajaxdata.aspx‘
  7 headers = {
  8     ‘authority‘: ‘it.ithome.com‘,
  9     ‘method‘: ‘POST‘,
 10     ‘path‘: ‘/ithome/getajaxdata.aspx‘,
 11     ‘scheme‘: ‘https‘,
 12     ‘accept‘: ‘text/html, */*; q=0.01‘,
 13     ‘accept-encoding‘: ‘gzip, deflate, br‘,
 14     ‘accept-language‘: ‘zh-CN,zh;q=0.9‘,
 15     ‘content-length‘: ‘40‘,
 16     ‘content-type‘: ‘application/x-www-form-urlencoded; charset=UTF-8‘,
 17     ‘cookie‘: ‘BAIDU_SSP_lcr=https://www.hao123.com/link/https/?key=http%3A%2F%2Fwww.ithome.com%2F&&monkey=m-kuzhan-group1&c=B329C2F33C91DEACCFAEB1680305F198; Hm_lvt_f2d5cbe611513efcf95b7f62b934c619=1530106766; ASP.NET_SessionId=tyxenfioljanx4xwsvz3s4t4; Hm_lvt_cfebe79b2c367c4b89b285f412bf9867=1530106547,1530115669; BEC=228f7aa5e3abfee5d059195ad34b4137|1530117889|1530109082; Hm_lpvt_f2d5cbe611513efcf95b7f62b934c619=1530273209; Hm_lpvt_cfebe79b2c367c4b89b285f412bf9867=1530273261‘,
 18     ‘origin‘: ‘https://it.ithome.com‘,
 19     ‘referer‘: ‘https://it.ithome.com/ityejie/‘,
 20     ‘user-agent‘: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3472.3 Safari/537.36‘,
 21     ‘x-requested-with‘: ‘XMLHttpRequest‘
 22 }
 23
 24 client = MongoClient()
 25 db = client[‘ithome‘]
 26 collection = db[‘ithome‘]
 27 max_page = 1000
 28
 29 def get_page(page):
 30
 31     formData = {
 32         ‘categoryid‘: ‘31‘,
 33         ‘type‘: ‘pccategorypage‘,
 34         ‘page‘: page,
 35         }
 36     try:
 37         r = requests.post(url, data=formData, headers=headers)
 38         if r.status_code == 200:
 39
 40             #print(type(r))
 41             html = r.text
 42             # 响应返回的是字符串，解析为HTML DOM模式 text = etree.HTML(html)
 43             text = etree.HTML(html)
 44             link_list = text.xpath(‘//h2/a/@href‘)
 45
 46             print("提取第"+str(page)+"页文章")
 47             id=0
 48             for link in link_list:
 49                 id+=1
 50                 print("解析第"+str(page)+"页第"+str(id)+"篇文章")
 51                 print("链接为："+link)
 52                 loadpage(link)
 53
 54     except requests.ConnectionError as e:
 55         print(‘Error‘, e.args)
 56
 57
 58 # 取出每个文章的链接
 59 def loadpage(link):
 60
 61     headers = {‘user-agent‘: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3472.3 Safari/537.36‘}
 62
 63     try:
 64
 65         reseponse = requests.get(link, headers = headers)
 66         if reseponse.status_code == 200:
 67             html = reseponse.text
 68             # 解析
 69             node = etree.HTML(html)
 70
 71             ithome ={}
 72             # 取出每个标题，正文等
 73
 74             # xpath返回的列表，这个列表就这一个参数，用索引方式取出来，标题
 75             ithome[‘title‘] = node.xpath(‘//*[@id="wrapper"]/div[1]/div[2]/h1‘)[0].text
 76             # 时间
 77             ithome[‘data‘] = node.xpath(‘//*[@id="pubtime_baidu"]‘)[0].text
 78             # 取出标签下的内容
 79             #content = node.xpath(‘//*[@id="paragraph"]/p/text()‘)
 80             ithome[‘content‘] = "".join(node.xpath(‘//*[@id="paragraph"]/p/text()‘)).strip()
 81             #content = node.xpath(‘//*[@id="paragraph"]/p‘)[1].text
 82             # 取出标签里包含的内容，作者
 83             ithome[‘author‘] = node.xpath(‘//*[@id="author_baidu"]/strong‘)[0].text
 84             # 评论数
 85             ithome[‘commentcount‘] = node.xpath(‘//span[@id="commentcount"]‘)[0].text
 86             #评论数没有取到
 87             write_to_file(ithome)
 88             save_to_mongo(ithome)
 89
 90     except requests.ConnectionError as e:
 91         print(‘Error‘, e.args)
 92
 93 def write_to_file(content):
 94     with open(‘ithome.json‘,‘a‘,encoding=‘utf-8‘) as f:
 95         f.write(json.dumps(content,ensure_ascii=False)+‘\n‘)
 96         f.close()
 97
 98 def save_to_mongo(result):
 99     if collection.insert(result):
100         print(‘Saved to Mongo‘)
101
102 if __name__ == ‘__main__‘:
103     for page in range(1, max_page + 1):
104         get_page(page)
105
106                         

原文地址：https://www.cnblogs.com/wanglinjie/p/9246369.html