猫眼电影TOP100榜

import re
import requests


def get_html(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36'}
    try:
        r = requests.get(url, headers=headers)
        r.raise_for_status()
        return r.text
    except:
        print('status_code is not 200')
        return None


def parse_html(text, info_list):
    pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?name"><a'
                         +'.*?>(.*?)</a>.*?star">\s+主演：(.*?)\s+</p>.*?releasetime">上映时间：(.*?)</p>'
                         +'.*?integer">(.*?)</i>.*?fraction">(.*?)</i>', re.S)
    items = re.findall(pattern, text)

    for item in items:
        info_list.append({
            'movie': item[1],
            'rank': item[0],
            'actors': item[2],
            'time': item[3],
            'score': item[4] + item[5]
           })


if __name__ == '__main__':
    url = 'http://maoyan.com/board/4'
    info_list = []
    for i in range(10):
        path = url + '?offset=' + str(i*10)
        txt = get_html(path)
        if txt:
            parse_html(txt, info_list)

    for info in info_list:
        print(info)

 

转载于:https://www.cnblogs.com/jp-mao/p/10005268.html