Python爬虫入门：爬取豆瓣电影TOP250

 1 # encoding = utf-8
 2 import codecs
 3 import requests
 4 from bs4 import BeautifulSoup
 5 
 6 # 爬取豆瓣电影TOP250
 7 
 8 DOWNLOADURL = ‘https://movie.douban.com/top250‘
 9 
10 def download_page(url): # 向服务器发送请求下载得到html
11     headers = {‘User-Agent‘: ‘Mozilla/4.0(compatibel; MSIE 5.5; Windows NT)‘} # 伪装成浏览器
12     data = requests.get(url, headers=headers).content
13     return data # 返回得到的html代码
14 
15 def parse_html(html): # 解析网页
16     soup = BeautifulSoup(html, ‘lxml‘) # 创建一个BeautifulSoup对象
17     movie_list_soup = soup.find(‘ol‘, attrs={‘class‘: ‘grid_view‘}) # 定位
18 
19     name_list = []
20     for movie_li in movie_list_soup.find_all(‘li‘): # 找到电影名字
21         detail = movie_li.find(‘div‘, attrs={‘class‘, ‘hd‘})
22         movie_name = detail.find(‘span‘, attrs={‘class‘, ‘title‘}).getText()
23         name_list.append(movie_name) # 放到一个list里面
24 
25     have_next = soup.find(‘span‘, attrs={‘class‘: ‘next‘}).find(‘a‘) # 找下一页的链接
26     if have_next: # 如果有下一页的链接不为空
27         return name_list, DOWNLOADURL + have_next[‘href‘] # 返回名字列表还有下一页的URL
28     else:
29         return name_list, None # 找不到返回None
30 
31 def main():
32     url = DOWNLOADURL
33     # with xxx.open as f 打开xxx之后finally关闭xxx
34     # codecs方便处理中文编码
35     with codecs.open(‘douban_movies‘, ‘wb‘, encoding=‘utf-8‘) as fp:
36         while url:
37             html = download_page(url)
38             name_list, url = parse_html(html)
39             #‘\n‘.join(name_list) : 以‘\n‘为分隔符将name_list所有元素合并成一个新的字符串
40             #‘{movies}‘.format(movies=‘xxxxx‘) : 即movies = ‘xxxxx‘,将xxxxx按照格式输出
41             fp.write(u‘{movies}\n‘.format(movies=‘\n‘.join(name_list)))
42 
43 if __name__ == ‘__main__‘:
44     main()