# -*- coding: utf-8 -*-
import urllib2
import sys
#BeautifulSoup3不需要修改,BeautifulSoup4,改成from bs4 import BeautifulSoup
from BeautifulSoup import BeautifulSoup
reload(sys)
sys.setdefaultencoding( "utf-8" )
def getcontent(url):
print url
req = urllib2.Request(url)
res = urllib2.urlopen(req)
magnetlist=[]
html = res.read()
res.close()
soup = BeautifulSoup(html)
#BeautifulSoup3不需要修改,BeautifulSoup4,改成soup.find_all('a')
allentry=soup.findAll('a')
for link in allentry:
if "magnet:"==link.get('href')[0:7]:
magnetlist.append(link.get('href'))
magnetlist = [line+'\n' for line in magnetlist]
f =open("magnet.txt", "a")
f.writelines(magnetlist)
f.close()
def main():
site="
http://bt.shousibaocai.com/search/"
keyword="地心引力"
keyword=urllib2.quote(keyword)
#总共抓前多少页
page=3
for i in range(1,page):
searchurl=site+keyword+"/"+str(i)
getcontent(searchurl)
if __name__ == '__main__':
main()
#end Jarett
这是一个专为移动设备优化的页面(即为了让你能够在 Google 搜索结果里秒开这个页面),如果你希望参与 V2EX 社区的讨论,你可以继续到 V2EX 上打开本讨论主题的完整版本。
https://www.v2ex.com/t/162375
V2EX 是创意工作者们的社区,是一个分享自己正在做的有趣事物、交流想法,可以遇见新朋友甚至新机会的地方。
V2EX is a community of developers, designers and creative people.