#coding=utf8
import urllib2
import codecs
import re
import time
from lxml import etree
url1 = 'http://521xunlei.com/portal.php'
path1 = '//*[@id="portal_block_62_content"]/div/ul/li[1]/a/@href'
path3 = '//*[@class="t_f"]/font/text()'
def geturlinfo(url,path,x):
request = urllib2.Request(url)
response = urllib2.urlopen(request)
result = response.read()
restree = etree.HTML(result)
nodes = restree.xpath(path)
if x == '1':
return nodes[0]
else:
i=0
open('thunder.txt','w').write('')
for node in nodes:
if re.search(':',node):
INFO = str(i)+': '+node.replace('\r\n','')
print INFO
open('thunder.txt','a').write(INFO.encode('utf8')+'\n')
i+=1
if __name__ == '__main__':
while True:
print '===================start===================\n'
url2 = 'http://'+url1.replace('http://','').split('/')[0]+'/'+geturlinfo(url1, path1,'1')
print 'GET From: '+url2
geturlinfo(url2, path3, '0')
time.sleep(24*3600)
#starts-with(@id,"test") id已test开头的
#首先获取对应div 再次xpath string(.) 组合
声明:我要去上班所有作品(图文、音视频)均由用户自行上传分享,仅供网友学习交流,版权归原作者Python乐园所有,原文出处。若您的权利被侵害,请联系删除。
本文标题:(爬虫获取php代码)(学爬虫用不用php)
本文链接:https://www.51qsb.cn/article/m9dlj.html