Python爬取猫眼电影排行

import requests
import pyquery


def crawl_page(url: str) -> None:
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) \
Chrome/72.0.3626.121 Safari/537.36',
    }
    response = requests.get(url, headers=headers)
    parse_page(response.text)


def parse_page(source_code: str) -> None:
    html = pyquery.PyQuery(source_code)
    dd_elements = html('.board-wrapper dd')
    for dd_element in dd_elements.items():
        data = {
            '排名': dd_element.find('i.board-index').text(),
            '电影名': dd_element.find('a.image-link').attr('title'),
            '主演': dd_element.find('p.star').text().split('：')[1],
            '上映时间': dd_element.find('p.releasetime').text().split('：')[1],
            '评分': dd_element.find('p.score').text(),
        }
        print(data)
        save_data(data)


def save_data(data: dict) -> None:
    data = str(data)
    with open('MaoYan.txt', 'a+', encoding='utf8') as f:
        f.write(data+'\n')
    return None


def main():
    for i in range(0, 100, 10):
        url = 'https://maoyan.com/board/4?offset={}'.format(i)
        crawl_page(url)


if __name__ == '__main__':
    main()

转载于:https://www.cnblogs.com/malinqing/p/11318341.html