欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  IT编程

Python爬取猫眼电影排行

程序员文章站 2023-11-30 15:39:34
```Python import requests import pyquery def crawl_page(url: str) -> None: headers = { 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleW... ......
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()