requests结合正则表达式爬取猫眼电影top100

最新推荐文章于 2020-02-29 12:00:51 发布

段小胖

最新推荐文章于 2020-02-29 12:00:51 发布

阅读量353

点赞数

本文链接：https://blog.csdn.net/dxcve/article/details/82747535

版权

import requests
import re
import json
def get_page(url):
    headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.92 Safari/537.36'}
    response = requests.get(url,headers=headers)
    if response.status_code==200:
        return response.text
    return None

def main():
    for offpage in range(0,10):        
        url = 'https://maoyan.com/board/4?offset='+str(offpage)
        html = get_page(url)
        content=parse_page(html)
        for res in content:
            write_file(res)

def parse_page(html):
    pattern = re.compile(
        '<dd>.*?board-.*?<p class="name".*?<a.*?>(.*?)</a>.*?<p.*?"star">(.*?)</p>.*?<p.*?"releasetime">(.*?)</p>.*?integer.*?>(.*?)</i>.*?fraction.*?>(.*?)</i>.*?</dd>',re.S) 
    items = re.findall(pattern,html)
    for item in items:
        yield [item[0].strip(),item[1].strip(),item[2].strip(),item[3]+item[4]]
        
def write_file(content):
    with open('猫眼电影.txt','a',encoding='utf-8') as f:
        result = json.dumps(content,ensure_ascii=False)
        f.write(result+'\n')


if __name__=='__main__':
        
    main()