python爬虫练习1:豆瓣电影TOP250

项目1:实现豆瓣电影TOP250标题爬取:

 1 from urllib.request import urlopen
 2 from bs4 import BeautifulSoup
 3 import re
 4
 5 class doubanSpider():
 6     def __init__(self):
 7         """
 8         初始化,
 9         页码,URL,存储数据,
10         """
11         self.page = 0;
12         # "http://movie.douban.com/top250?start=25&filter=&type=" 第二页
13         # 第一页
14         self.cur_url = "http://movie.douban.com/top250?start=0&filter=&type="
15         self.datas = []
16
17     def claw(self):
18         while self.page<10:
19             self.downloadURL()
20             self.updateURL()
21         self.output()
22
23     def updateURL(self):
24         self.page+=1
25         self.cur_url.replace("start=0","start="+str(self.page*25))
26
27     def downloadURL(self):
28         html = urlopen(self.cur_url)
29         bsObj = BeautifulSoup(html,"html.parser")
30         datas = bsObj.findAll("span", {"class": "title"})
31         for data in datas:
32             str = data.get_text()
33             if "\xa0/\xa0" not in str:
34                 self.datas.append(str)
35
36     def output(self):
37         num = 1
38         for data in self.datas:
39             print("TOP"+str(num)+": " +data)
40             num+=1
41
42 if __name__ == "__main__":
43     print("豆瓣电影TOP250:python抓取")
44     myspider = doubanSpider()
45     myspider.claw()