0
我登录到我的帐户,如:保持登录和使用Python请求模块设置cookie的,做的东西
import os
import requests
from lxml import html
def GetContent(url):
response = requests.get(url)
return response.content
def Parser(content):
tree = html.fromstring(content)
return [e.text_content() for e in tree.xpath('//div[@class="group"]/div[@class="groupinfo"]/a')]
def Func():
try:
s = requests.Session()
email='user'
password='123456'
post_data={'email':email, 'password':password}
post_response=s.post(url='http://site.ir/signin/', data=post_data)
resultfile = open("result.txt", "w+")
page=1
while (page<=750):
print
print 'Checking page number: ', page
url2 = 'http://site.ir/' + str(page)
print "URL: " + url2
content = GetContent(url2)
results = Parser(content)
for i in results:
print i
resultfile.writelines(i+'\n')
resultfile.flush()
page += 1
resultfile.close()
except (KeyboardInterrupt, SystemExit):
print "\nKeyboardInterruption with Ctrl+c signal"
sys.exit(1)
if __name__ == "__main__":
Func()
我想留洛和做的东西。正如你在代码中看到的那样,我做了一个会话
当页面正在增加时我希望保持登录状态并获取下一页的内容并执行其他操作,,,但它仅返回页面编号为1的内容而页面正在增加。
谢谢...错误'类型错误:预期字符串或buffer'出现 – MLSC 2014-09-25 18:27:18
'打印content'的输出是'<响应[200]>' – MLSC 2014-09-25 18:29:16
你知不知道热来解决它? – MLSC 2014-09-25 18:34:12