requests简单实现

不爱缺氧i

已于 2023-07-16 07:07:03 修改

阅读量67

点赞数

分类专栏： python 爬虫文章标签： python

于 2023-07-16 05:31:39 首次发布

本文链接：https://blog.csdn.net/qq_38236017/article/details/131746582

版权

python 同时被 2 个专栏收录

6 篇文章 0 订阅

订阅专栏

爬虫

2 篇文章 0 订阅

订阅专栏

import requests
import re
#爬取豆瓣top250
def get250(count):
    f = open(r'top250.csv', 'w', encoding='utf-8')
    head = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.87 Safari/537.36 SE 2.X MetaSr 1.0"
    }
    url = 'https://movie.douban.com/top250?start=%s&filter='% count
    rq = requests.get(url, headers=head)
    r = rq.text
    obj = re.compile(r'<div class="item">.*?<div class="pic">.*?<em class="">(?P<id>\d+)</em>.*?<a href.*?<img width="100" alt="(?P<name>.*?)" src=.*?导演:(?P<dao>.*?)&nbsp;.*?property="v:average">(?P<fen>\d+.\d)</span>.*?<span class="inq">(?P<ping>.*?)</span>'
                     , re.S)
    result = obj.finditer(r)
    for item in result:
        id = item.group("id")
        name = item.group("name")
        dao = item.group("dao")
        fen = item.group("fen")
        ping = item.group("ping")
        print(id, name, dao, fen, ping)
        f.write(f"{id},{name},{dao},{fen},{ping}\n")
if __name__ == '__main__':
    count = 0
    for i in range(10):
        get250(count)
        count += 25