抓取猫眼top100电影排行

import requests
import re
import json
import time
#抓取目标第一页函数
def get_first_page(url):
    headers = {
        'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
    }
    response = requests.get(url, headers = headers)
    if response.status_code == 200:
        return response.text
    return None
#定义解析源码函数
def parse_the_page(html):
    pattern = re.compile(
        '<dd>.*?board-index.*?>(.*?)</i>.*?data-src="(.*?)".*?alt="(.*?)".*?</a>.*?star.*?>(.*?)</p>.*?releasetime.*?>(.*?)</p>.*?movie-item-number score-num.*?integer.*?>(.*?)</i>.*?fraction.*?>(.*?)</i>.*?</dd>', re.S
    )
    items = re.findall(pattern, html)
    for item in items:
        yield {
            'index': item[0],
            'image': item[1],
            'title': item[2].strip(),
            'actor': item[3].strip(),
            'time': item[4].strip(),
            'score': item[5].strip()+item[6].strip()
        }
#定义写入文件函数
def write_to_file(content):
    with open('maoyan-top-100.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False)+'\n')
#定义main
def main(offset):
    url = 'http://maoyan.com/board/4?offset=' + str(offset)
    html = get_first_page(url)
    for item in parse_the_page(html):
        print(item)
        write_to_file(item)
#start
if __name__ == '__main__':
    for i in range(10):
        main(offset = i * 10)
        time.sleep(1)