requests + bs4 爬取豆瓣 top250 电影信息

  • Post author:
  • Post category:其他


"""
爬取豆瓣top250个电影
"""
import requests
import bs4
import re


def open_url(url):
    headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36'}
    res = requests.get(url, headers=headers)
    return res


def find_movies(res):
    """
    使用bs4 对网页内容进行解析
    :param res:
    :return:
    """
    soup = bs4.BeautifulSoup(res.text, 'html.parser')
    # 电影名
    movies = []
    targets = soup.find_all('div', class_="hd")
    for each in targets:
        movies.append(each.a.span.text)

    # 评分
    ranks = []
    targets = soup.find_all('span', class_='rating_num')
    for each in targets:
        ranks.append(each.text)

    # 资料
    messages = []
    targets = soup.find_all('div', class_='bd')
    for each in targets:
        try:
            messages.append(each.p.text.split('\n')[1].strip() + each.p.text.split('\n')[2].strip())
        except:
            continue

    result = []
    length = len(movies)
    for i in range(length):
        result.append(movies[i] + ranks[i] + messages[i] + '\n')

    return result


def find_depth(res):
    """
    找出一共有多少个页面
    :param res:
    :return:
    """
    soup = bs4.BeautifulSoup(res.text, 'html.parser')
    depth = soup.find('span', class_='next').previous_sibling.previous_sibling.text
    return int(depth)


def main():
    host = 'https://movie.douban.com/top250'
    res = open_url(host)
    depth = find_depth(res)
    result = []
    for i in range(depth):
        url = host + "?start=" + str(25*i)
        res = open_url(url)
        result.extend(find_movies(res))
    with open('douban_250.txt', 'w', encoding='utf-8') as f:
        for each in result:
            f.write(each)
    return


if __name__ == '__main__':
    main()
    pass



版权声明:本文为GYK0812原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明。