抓取猫眼电影排行T100

import requests
import json
from requests.exceptions import RequestException
import re
import time

# 抓取首页
def get_one_page(url):
    try:
        headers = {
        'User-Agent': 'Mozilla/5.0(Macintosh; Inter Mac OS X 10_13_3) AppleWebKit/537.36(KHTML, like Gecko) Chrome/65.0.3323.162. Safari/537.36'
        }
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None
        
def parse_one_page(html):
    pattern = re.compile('
.*?board-index.*?>(.*?).*?data-src="(.*?)".*?name.*?a.*?>(.*?).*?star.*?>(.*?)
.*?releasetime.*?>(.*?)
.*?integer.*?>(.*?).*?fraction.*?>(.*?).*?
', 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()[3:],
            'time':item[4].strip()[5:],
            'score':item[5] + item[6]
        }
    
def write_to_file(content):
    with open('MaoYanTop100.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False)+'\n')
        
def main(offset):
    url = 'http://maoyan.com/board/4?offset=' + str(offset)
    html = get_one_page(url)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)

if __name__ == '__main__':
    for i in range(10):
        main(offset=i * 10)
        time.sleep(1)

参考：《Python3网络爬虫开发实战》崔庆才