爬取IT之家新闻

Posted 2020-11-20 wanglinjie

 

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 
  5 
  6 url = ‘https://it.ithome.com/ithome/getajaxdata.aspx‘
  7 
  8 headers = {
  9 
 10 
 11     ‘authority‘: ‘it.ithome.com‘,
 12     ‘method‘: ‘POST‘,
 13     ‘path‘: ‘/ithome/getajaxdata.aspx‘,
 14     ‘scheme‘: ‘https‘,
 15     ‘accept‘: ‘text/html, */*; q=0.01‘,
 16     ‘accept-encoding‘: ‘gzip, deflate, br‘,
 17     ‘accept-language‘: ‘zh-CN,zh;q=0.9‘,
 18     ‘content-length‘: ‘40‘,
 19     ‘content-type‘: ‘application/x-www-form-urlencoded; charset=UTF-8‘,
 20     ‘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‘,
 21     ‘origin‘: ‘https://it.ithome.com‘,
 22     ‘referer‘: ‘https://it.ithome.com/ityejie/‘,
 23     ‘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‘,
 24     ‘x-requested-with‘: ‘XMLHttpRequest‘
 25 } 
 26 
 27 
 28 max_page = 1000
 29 
 30 def get_page(page):  
 31 
 32     formData = {
 33         ‘categoryid‘: ‘31‘,
 34         ‘type‘: ‘pccategorypage‘,
 35         ‘page‘: page,
 36         }
 37     r = requests.post(url, data=formData, headers=headers)
 38     #print(type(r))
 39     html = r.text
 40     # 响应返回的是字符串，解析为HTML DOM模式 text = etree.HTML(html)
 41     #print(html)
 42     text = etree.HTML(html)
 43     #print(type(text))
 44 
 45     #link_list = text.xpath(‘//*[@id="wrapper"]/div[1]/div[1]/ul[1]/li/div/h2/a/@href‘) 
 46     link_list = text.xpath(‘//h2/a/@href‘) 
 47     #result = etree.tostring(text)
 48     #print(result)
 49     #print(link_list)
 50     #print(page)
 51     print("提取第"+str(page)+"页文章")
 52     id=0
 53     for link in link_list:
 54         id+=1
 55         print("解析第"+str(page)+"页第"+str(id)+"篇文章")
 56         print("链接为："+link)
 57         loadpage(link)
 58 
 59 
 60 # 取出每个文章的链接
 61 def loadpage(link):
 62 
 63     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‘}
 64   
 65     reseponse = requests.get(link, headers = headers)
 66     html = reseponse.text
 67     # 解析
 68 
 69     node = etree.HTML(html)
 70 
 71     #text = etree.HTML(html)
 72     # 取出每层发送的文章链接集合
 73     #result = etree.tostring(text)
 74     #print(result.decode(‘utf-8‘))
 75     #print(type(result))
 76 
 77     items ={}
 78     # 取出每个标题，正文等
 79     #for node in text:
 80     #用循环的话，一个页面会执行两次for，内容会重复。
 81     print(node)
 82 
 83     # 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
 84     title = node.xpath(‘//*[@id="wrapper"]/div[1]/div[2]/h1‘)[0].text
 85     # 时间
 86     data = node.xpath(‘//*[@id="pubtime_baidu"]‘)[0].text
 87     # 取出标签下的内容
 88     content = "".join(node.xpath(‘//*[@id="paragraph"]/p/text()‘)).strip()
 89     #content = node.xpath(‘//*[@id="paragraph"]/p‘)[1].text
 90     # 取出标签里包含的内容，作者
 91     author = node.xpath(‘//*[@id="author_baidu"]/strong‘)[0].text
 92     # 评论数
 93     commentcount = node.xpath(‘//span[@id="commentcount"]‘)[0].text
 94     #评论数没有取到
 95 
 96 
 97     items = {
 98         "title" : title,
 99         "data" : data,
100         "content" : content,
101         "author" : author,
102         "commentcount" : commentcount
103     } 
104 
105     print("--正在保存--")
106     with open("ithome.json", "a") as f:
107             #f.write(json.dumps(items, ensure_ascii = False).encode("utf-8") + "
")
108         f.write(json.dumps(items, ensure_ascii = False) + "
")
109     print("--已保存--")
110 
111 
112 
113 if __name__ == "__main__":  
114     
115     for page in range(1, max_page + 1):
116         get_page(page)