Ich versuche, die HTML-Seite vom Senden einer POST-Anforderung zurückzubekommen:
import httplib
import urllib
import urllib2
from BeautifulSoup import BeautifulSoup
headers = {
'Host': 'digitalvita.pitt.edu',
'Connection': 'keep-alive',
'Content-Length': '325',
'Origin': 'https://digitalvita.pitt.edu',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_4) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1',
'Content-type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Accept': 'text/javascript, text/html, application/xml, text/xml, */*',
'Referer': 'https://digitalvita.pitt.edu/index.php',
'Accept-Encoding': 'gzip,deflate,sdch',
'Accept-Language': 'en-US,en;q=0.8',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
'Cookie': 'PHPSESSID=lvetilatpgs9okgrntk1nvn595'
}
data = {
'action': 'search',
'xdata': '<search id="1"><context type="all" /><results><ordering>familyName</ordering><pagesize>100000</pagesize><page>1</page></results><terms><name>d</name><school>All</school></terms></search>',
'request': 'search'
}
data = urllib.urlencode(data)
print data
req = urllib2.Request('https://digitalvita.pitt.edu/dispatcher.php', data, headers)
response = urllib2.urlopen(req)
the_page = response.read()
soup=BeautifulSoup(the_page)
print soup
Kann mir jemand sagen, wie ich das machen kann?