我尝试使用漂亮的汤解析链接时收到以下错误,看起来身份验证失败....如何验证链接?
from bs4 import BeautifulSoup
import argparse
import urllib
import urllib2
import getpass
import re
def update (searchurl):
page = urllib2.urlopen(searchurl)
soup = BeautifulSoup(page)
#print(soup.textarea.string)
print(soup.get_text())
def main ():
#For logging
print "test"
parser = argparse.ArgumentParser(description='This is the update.py script created by test')
parser.add_argument('-u','--url',action='store',dest='url',default=None,help='<Required> url link',required=True)
results = parser.parse_args()# collect cmd line args
url = results.url
#print url
update(url)
if __name__ == '__main__':
main()
以下是尝试打开链接时的错误
Traceback (most recent call last):
File "announce_update2.py", line 24, in <module>
main()
File "announce_update2.py", line 22, in main
update(url)
File "announce_update2.py", line 9, in update
page = urllib2.urlopen(searchurl)
File "C:\Python27\lib\urllib2.py", line 126, in urlopen
return _opener.open(url, data, timeout)
File "C:\Python27\lib\urllib2.py", line 406, in open
response = meth(req, response)
File "C:\Python27\lib\urllib2.py", line 519, in http_response
'http', request, response, code, msg, hdrs)
File "C:\Python27\lib\urllib2.py", line 438, in error
result = self._call_chain(*args)
File "C:\Python27\lib\urllib2.py", line 378, in _call_chain
result = func(*args)
File "C:\Python27\lib\urllib2.py", line 625, in http_error_302
return self.parent.open(new, timeout=req.timeout)
File "C:\Python27\lib\urllib2.py", line 406, in open
response = meth(req, response)
File "C:\Python27\lib\urllib2.py", line 519, in http_response
'http', request, response, code, msg, hdrs)
File "C:\Python27\lib\urllib2.py", line 444, in error
return self._call_chain(*args)
File "C:\Python27\lib\urllib2.py", line 378, in _call_chain
result = func(*args)
File "C:\Python27\lib\urllib2.py", line 527, in http_error_default
raise HTTPError(req.get_full_url(), code, msg, hdrs, fp)