[Python]爬取首都之窗百姓信件网址id python 2020.2.13

 1 import json
 2 import requests
 3 import io
 4 
 5 url="http://www.beijing.gov.cn/hudong/hdjl/com.web.search.mailList.mailList.biz.ext"
 6 
 7 kv = {
 8     ‘Host‘: ‘www.beijing.gov.cn‘,
 9     ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:71.0) Gecko/20100101 Firefox/71.0‘,
10     ‘Accept‘: ‘application/json, text/javascript, */*; q=0.01‘,
11     ‘Accept-Language‘: ‘zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2‘,
12     ‘Accept-Encoding‘: ‘gzip, deflate‘,
13     ‘Content-Type‘: ‘text/json‘,
14     ‘X-Requested-With‘: ‘XMLHttpRequest‘,
15     ‘Content-Length‘: ‘155‘,
16     ‘Origin‘: ‘http://www.beijing.gov.cn‘,
17     ‘Connection‘: ‘keep-alive‘,
18     ‘Referer‘: ‘http://www.beijing.gov.cn/hudong/hdjl/‘}
19 
20 def page(begin):
21     query={
22     ‘PageCond/begin‘: begin,
23     ‘PageCond/isCount‘:‘true‘,
24     ‘PageCond/length‘:6,
25     }
26     datas=json.dumps(query)
27     r=requests.post(url,data=datas,headers=kv)
28     print(r.status_code)
29     print(r.text)
30     js=json.loads(r.text)
31     for j in js["mailList"]:
32         print(j)
33         print(j.get("original_id"))
34 
35 
36 def href():
37     begin=0
38     for i in range(0,5584):
39         if i%6==0:
40             page(i)
41             #print(begin)
42 
43 if __name__=="__main__":
44     href()