爬取糗事百科[文字]栏前十页_爬取糗事百科推荐页面中第1到10

import urllib.request
import re



def jokeCrawer(url):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.3.4000 Chrome/30.0.1599.101 Safari/537.36"
    }
    req = urllib.request.Request(url, headers=headers)
    response = urllib.request.urlopen(req)

    HTML = response.read().decode('utf-8')

    pat = r'<div class="author clearfix">(.*?)<span class="stats-vote"><i class="number">'
    re_joke = re.compile(pat, re.S)
    divsList = re_joke.findall(HTML)
    # print(divsList)
    # print(len(divsList))
    dic = {}
    for div in divsList:
        # 用户名
        re_u = re.compile(r'<h2>(.*?)</h2>', re.S)
        username = re_u.findall(div)
        username = username[0]

        # 段子
        re_d = re.compile(r'<div class="content">\n<span>(.*?)</span>', re.S)
        duanzi = re_d.findall(div)
        duanzi = duanzi[0]
        # print(duanzi)

        dic[username] = duanzi


    return dic



    # with open(r'E:\all-workspace\qianfeng\0802-爬虫简介与json\file\file3.html', 'w') as f:
    #     f.write(HTML)

for i in range(1,10):
    url = "https://www.qiushibaike.com/text/page/str(i)/"
    info = jokeCrawer(url)
    for k, v in info.items():
        print(k+"说"+ v)










1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58