Python crawler 豆瓣电影排行榜评分

最新推荐文章于 2024-05-12 10:00:56 发布

YangHeng816

最新推荐文章于 2024-05-12 10:00:56 发布

阅读量1.5k

点赞数

分类专栏： Python Scripts 文章标签： python crawler 豆瓣排行榜

本文链接：https://blog.csdn.net/YangHeng816/article/details/52750156

版权

Python Scripts 专栏收录该内容

15 篇文章 0 订阅

订阅专栏

# coding:utf-8

"""
 获取豆瓣电影评分排行榜,requests负责请求并加载网页，BeautifulSoup 用于解析html文档.
"""
import requests
import sys
# import lxml
from bs4 import BeautifulSoup
# from datetime import datetime, timedelta
reload(sys)
sys.setdefaultencoding('utf8')


# 获得指定开始排行的电影url
def get_url(root_url, start):
    return root_url+"?start="+str(start)+"&filter="


# 根据传入的url，获取电影排名及评分
def get_review(page_url):
    movies_list = []
    response = requests.get(page_url)
    soup = BeautifulSoup(response.text, "lxml")
    soup = soup.find('ol', 'grid_view')
    for tag_li in soup.find_all('li'):
        dict = {}
        dict['rank'] = tag_li.find('em').string
        dict['name'] = tag_li.find_all('span', 'title')[0].string
        dict['score'] = tag_li.find('span', 'rating_num').string
        if tag_li.find('span', 'inq'):
            dict['desc'] = tag_li.find('span', 'inq').string
        movies_list.append(dict)
    return movies_list

if __name__ == "__main__":
    root_url = "https://movie.douban.com/top250"
    start = 0
    while start < 100:
        movies_list = get_review(get_url(root_url, start))
        for movie_dict in movies_list:
            print('电影排名：'+movie_dict['rank'])
            print('电影名称：'+movie_dict.get('name'))
            print('电影评分：'+movie_dict.get('score'))
            print('电影评词：'+movie_dict.get('desc','无评词'))
            print('------------------------------------------------------')
        start += 25