Fork me on Github

爬取bean half Top250 

 1 import re
 2 import requests
 3 import csv
 4 
 5 url = 'https://movie.douban.com/top250'
 6 
 7 header = {
 8     "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
 9                   "Chrome/60.0.3100.0 Safari/537.36 "
10 }
11 
12 index = 0
13 while index < 10:
14     param = {
15         "start": index * 25
16     }
17     res = requests.get(url, headers=header, params=param)
18     pageContent = res.text
19 
20     # 正则表达式解析数据
21     obj = re.compile(r'<li>.*?<span class="title">(?P<name>.*?)'
22                      r'</span>.*?<p class="">.*?<br>(?P<year>.*?)&nbsp;/&nbsp;'
23                      r'(?P<place>.*?)&nbsp;.*?</p>', re.S)
24 
25     result = obj.finditer(pageContent)
26 
27     f = open('csv/top250.csv', mode='a+', encoding='utf-8')
28     csvWriter = csv.writer(f)
29     num = 1
30     for i in result:
31         dic = i.groupdict()
32         dic['year'] = dic['year'].strip()
33         print(dic.values())
34         csvWriter.writerow(dic.values())
35         num = num+1
36     f.close()
37     index = index + 1

 

posted @ 2022-05-29 22:41  昂昂呀  阅读(31)  评论(0)    收藏  举报