I am trying to work on some code that will fetch all hyperlinks from a webpage url using the python.
The code works perfectly fine when i try to run the code at home network without my proxy. When i have to show the code to my teacher in my University - it would never work because of the proxy my University is using . Its proxy that all students use to connect to the internet is proxy4.nehu.ac.in how do i code so that it will go through the proxyport. please help i have been trying other stuff by no luck for so many days.
my code is :
import sys
import urllib
import urlparse
from bs4 import BeautifulSoup
def process(url):
page = urllib.urlopen(url)
text = page.read()
page.close()
soup = BeautifulSoup(text)
with open('s.txt','w') as file:
for tag in soup.findAll('a', href=True):
tag['href'] = urlparse.urljoin(url, tag['href'])
print tag['href']
file.write('\n')
file.write(tag['href'])
def main():
if len(sys.argv) == 1:
print 'No url !!'
sys.exit(1)
for url in sys.argv[1:]:
this is the error
Traceback (most recent call last):
File "myurl.py", line 26, in <module>
main()
File "myurl.py", line 24, in main
process(url)
File "myurl.py", line 7, in process
page = urllib.urlopen(url)
File "/usr/lib/python2.7/urllib.py", line 84, in urlopen
return opener.open(url)
File "/usr/lib/python2.7/urllib.py", line 205, in open
return getattr(self, name)(url)
File "/usr/lib/python2.7/urllib.py", line 342, in open_http
h.endheaders(data)
File "/usr/lib/python2.7/httplib.py", line 940, in endheaders
self._send_output(message_body)
File "/usr/lib/python2.7/httplib.py", line 803, in _send_output
self.send(msg)
File "/usr/lib/python2.7/httplib.py", line 755, in send
self.connect()
File "/usr/lib/python2.7/httplib.py", line 736, in connect
self.timeout, self.source_address)
File "/usr/lib/python2.7/socket.py", line 551, in create_connection
for res in getaddrinfo(host, port, 0, SOCK_STREAM):
IOError: [Errno socket error] [Errno -2] Name or service not known''