最简单的爬虫示例

import urllib.request
from bs4 import BeautifulSoup as bs #引包

url='https://movie.douban.com/nowplaying/hangzhou/' #要爬取的地址连接
data=urllib.request.urlopen(url).read() #使用urllib取请求url 并读取返回的信息，类似与response
data=data.decode("UTF-8") # 编码转换，默认是GBK
soup = bs(data, 'html.parser') #将响应的数据转换成html
nowplaying_movie = soup.find_all('div', id='nowplaying') #取html 页面 id为nowplaying 的元素节点
nowplaying_movie_list = nowplaying_movie[0].find_all('li', class_='list-item') #
nowplaying_list = []    
for item in nowplaying_movie_list:
nowplaying_dict = {} 
nowplaying_dict['id'] = item['data-subject']
nowplaying_dict['score'] = item['data-score'] 
nowplaying_dict['actors'] = item['data-actors']
for tag_img_item in item.find_all('img'):            
nowplaying_dict['name'] = tag_img_item['alt']            
nowplaying_list.append(nowplaying_dict)
file=open("html.txt","w+") # 打开或者创建一个为html.txt 文件，拥有读写权限
file.write(str(nowplaying_list)) #将nowplaying_list 列表当作字符串输出在文件中
print(nowplaying_list)