6.14python作业
爬取豆瓣TOP250电影信息
显示:电影详情页url、图片链接、电影名称、导演、主演、电影上映时间、电影评分、评价人数、简介
代码如下:
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
import requests import re headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36' } base_url = 'https://movie.douban.com/top250?start={}&filter=' n = 0 for line in range(10): url = base_url.format(n) print(type(n)) n += 25 print(url) # 1、往豆瓣TOP250发送请求获取响应数据 response = requests.get(url, headers=headers) # print(response.text) # 2、通过正则解析提取数据 # 电影详情页url、图片链接、电影名称、电影评分、评价人数 movie_content_list = re.findall( # 正则规则 # '<div class="item">.*?href="(.*?)">.*?src="(.*?)".*?<span class="title">(.*?)</span>.*?<span class="rating_num".*?>(.*?)</span>.*?<span>(.*?)人评价', '<div class="item">.*?href="(.*?)">.*?src="(.*?)" class="">.*?<span class="title">(.*?)</span>.*?<div class="bd">.*?导演:(.*?)<br>(.*?)</p>.*?<span class="rating_num".*?>(.*?)</span>.*?<span>(.*?)人评价.*?<span class="inq">(.*?)</span>', # 解析文本 response.text, # 匹配模式 re.S) for movie_content in movie_content_list: # 解压赋值每一部电影 detail_url, movie_jpg, name, daoyan, timer,point, num, desc= movie_content data = f'电影名称:{name}, 详情页url:{detail_url}, 图片url:{movie_jpg}, 导演: {daoyan} 上映时间: {timer}评分: {point}, 评价人数: {num} 简介:{desc}\n' print(data) # 3、保存数据,把电影信息写入文件中 with open('douban.txt', 'a', encoding='utf-8') as f: f.write(data)
运行结果: