I was making my project on mac and I tried to do the same things by Beagle Bone Black(BBB).
However, I couldn't use urllib in BBB so I am stuck: I cannot go forward.(it is working well in my mac)
I tried this simple code as an example:
import urllib
conn = urllib.urlopen('http://stackoverflow.com/questions/8479736/using-python-urllib-how-to-avoid-non-html-content')
then this Error occurred:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/lib/python2.7/urllib.py", line 86, in urlopen
return opener.open(url)
File "/usr/lib/python2.7/urllib.py", line 207, in open
return getattr(self, name)(url)
File "/usr/lib/python2.7/urllib.py", line 351, in open_http
'got a bad status line', None)
IOError: ('http protocol error', 0, 'got a bad status line', None)
I need to fetch a html data for my project.
How can I solve this problem? Do you have any ideas ?
Thank you.
When I tried urllib2
I got this:
>>> import urllib2
>>> conn = urllib2.urlopen('http://stackoverflow.com/questions/8479736/using-python-urllib-how-to-avoid-non-html-content')
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/lib/python2.7/urllib2.py", line 126, in urlopen
return _opener.open(url, data, timeout)
File "/usr/lib/python2.7/urllib2.py", line 400, in open
response = self._open(req, data)
File "/usr/lib/python2.7/urllib2.py", line 418, in _open
'_open', req)
File "/usr/lib/python2.7/urllib2.py", line 378, in _call_chain
result = func(*args)
File "/usr/lib/python2.7/urllib2.py", line 1207, in http_open
return self.do_open(httplib.HTTPConnection, req)
File "/usr/lib/python2.7/urllib2.py", line 1180, in do_open
r = h.getresponse(buffering=True)
File "/usr/lib/python2.7/httplib.py", line 1030, in getresponse
response.begin()
File "/usr/lib/python2.7/httplib.py", line 407, in begin
version, status, reason = self._read_status()
File "/usr/lib/python2.7/httplib.py", line 371, in _read_status
raise BadStatusLine(line)
httplib.BadStatusLine: ''
Also I tried this:
curl http://stackoverflow.com/questions/8479736/using-python-urllib-how-to-avoid-non-html-content
curl: (52) Empty reply from server
and this:
wget http://stackoverflow.com/questions/8479736/using-python-urllib-how-to-avoid-non-html-content
Connecting to stackoverflow.com (198.252.206.16:80)
wget: error getting response
but they didn't work
at home, I also tried and failed but returns a different error:
conn = urllib2.urlopen('http://stackoverflow.com/questions/8479736/using-python-urllib-how-to-avoid-non-html-content')
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/lib/python2.7/urllib2.py", line 126, in urlopen
return _opener.open(url, data, timeout)
File "/usr/lib/python2.7/urllib2.py", line 400, in open
response = self._open(req, data)
File "/usr/lib/python2.7/urllib2.py", line 418, in _open
'_open', req)
File "/usr/lib/python2.7/urllib2.py", line 378, in _call_chain
result = func(*args)
File "/usr/lib/python2.7/urllib2.py", line 1215, in https_open
return self.do_open(httplib.HTTPSConnection, req)
File "/usr/lib/python2.7/urllib2.py", line 1177, in do_open
raise URLError(err)
urllib2.URLError: <urlopen error [Errno -2] Name or service not known>
environment
BBB: Linux beaglebone 3.8.13 #1 SMP Tue Jun 18 02:11:09 EDT 2013 armv7l GNU/Linux
python version: 2.7.3
I'm really want to recommend you requests lib:
>>> r = requests.get('https://api.github.com/user', auth=('user', 'pass'))
>>> r.status_code
200
>>> r.headers['content-type']
'application/json; charset=utf8'
>>> r.encoding
'utf-8'
>>> r.text
u'{"type":"User"...'
http://www.python-requests.org/en/latest/
How to install:
sudo pip install requests
Related
I am trying to connect to an API using python 2.7.
Code:
from urllib import urlencode
import urllib2
def http_post(url, data):
post = urlencode(data)
req = urllib2.Request(url, post)
response = urllib2.urlopen(req)
return response.read()
Error:
>>> r = http_post(LOGIN_URL, PARAMS)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "<stdin>", line 4, in http_post
File "/usr/local/lib/python2.7/urllib2.py", line 127, in urlopen
return _opener.open(url, data, timeout)
File "/usr/local/lib/python2.7/urllib2.py", line 404, in open
response = self._open(req, data)
File "/usr/local/lib/python2.7/urllib2.py", line 422, in _open
'_open', req)
File "/usr/local/lib/python2.7/urllib2.py", line 382, in _call_chain
result = func(*args)
File "/usr/local/lib/python2.7/urllib2.py", line 1222, in https_open
return self.do_open(httplib.HTTPSConnection, req)
File "/usr/local/lib/python2.7/urllib2.py", line 1184, in do_open
raise URLError(err)
urllib2.URLError: <urlopen error [Errno -5] No address associated with hostname
Similar code in python 3.5 is running.
It looks like the url is not being found.
Have you defined LOGIN_URL just above the output we see in your "Error:" extract?
i want to scraping "www.naver.com"
so i tried to scraping using open api
i wrote code following this:
import urllib.request
import urllib.parse
from bs4 import BeautifulSoup
defaultURL = 'http://openapi.naver.com/search?&'
key = 'key=keyvalue'
target='&target=news'
sort='&sort=sim'
start='&start=1'
display='&display=100'
query='&query='+urllib.parse.quote_plus(str(input("write:")))
fullURL=defaultURL+key+target+sort+start+display+query
print(fullURL)
file=open("C:\\Users\\kimty\\Desktop\\k\\python\\N\\naver_news.txt","w",encoding='utf-8')
f=urllib.request.urlopen(fullURL)
resultXML=f.read()
xmlsoup=BeautifulSoup(resultXML,'html.parser')
items=xmlsoup.find._all('item')
for item in items:
file.write('---------------------------------------\n')
file.write('title :'+item.tile.get_text(strip=True)+'\n')
file.write('contents : '+item.description.get_text(strip=True)+'\n')
file.write('\n')
file.close()
but python shell only show this
============= RESTART: C:\Users\kimty\Desktop\kpython\N\N.py =============
write:lee
http://openapi.naver.com/search?&key=keyvalue&target=news&sort=sim&start=1&display=100&query=lee
Traceback (most recent call last):
File "C:\Users\kimty\Desktop\k\python\N\N.py", line 19, in <module>
f=urllib.request.urlopen(fullURL)
File "C:\Python34\lib\urllib\request.py", line 161, in urlopen
return opener.open(url, data, timeout)
File "C:\Python34\lib\urllib\request.py", line 464, in open
response = self._open(req, data)
File "C:\Python34\lib\urllib\request.py", line 482, in _open
'_open', req)
File "C:\Python34\lib\urllib\request.py", line 442, in _call_chain
result = func(*args)
File "C:\Python34\lib\urllib\request.py", line 1211, in http_open
return self.do_open(http.client.HTTPConnection, req)
File "C:\Python34\lib\urllib\request.py", line 1186, in do_open
r = h.getresponse()
File "C:\Python34\lib\http\client.py", line 1227, in getresponse
response.begin()
File "C:\Python34\lib\http\client.py", line 386, in begin
version, status, reason = self._read_status()
File "C:\Python34\lib\http\client.py", line 356, in _read_status
raise BadStatusLine(line)
http.client.BadStatusLine: ''
why this happening?
what about that python shell talk to me?
i am using windows 8.1 64x, python 3.4.4
This http.client.BadStatusLine is a subclass of http.client.HTTPException. It gave you a http error back, maybe your API key is wrong! If I try to access the link with my browser it also gives me an error.
This is the exact address you tried to request.
Edit
Some people have fixed this error by importing the http lib.
I wanted to execute this code I found on the python website:
#!/usr/bin/python
import urllib2
f = urllib2.urlopen('http://www.python.org/')
print f.read(100)
but the result was this:
Traceback (most recent call last):
File "WebServiceAusführen.py", line 5, in <module>
f = urllib2.urlopen('http://www.python.org/')
File "/usr/lib/python2.7/urllib2.py", line 126, in urlopen
return _opener.open(url, data, timeout)
File "/usr/lib/python2.7/urllib2.py", line 400, in open
response = self._open(req, data)
File "/usr/lib/python2.7/urllib2.py", line 418, in _open
'_open', req)
File "/usr/lib/python2.7/urllib2.py", line 378, in _call_chain
result = func(*args)
File "/usr/lib/python2.7/urllib2.py", line 1207, in http_open
return self.do_open(httplib.HTTPConnection, req)
File "/usr/lib/python2.7/urllib2.py", line 1146, in do_open
h = http_class(host, timeout=req.timeout) # will parse host:port
File "/usr/lib/python2.7/httplib.py", line 693, in __init__
self._set_hostport(host, port)
File "/usr/lib/python2.7/httplib.py", line 721, in _set_hostport
raise InvalidURL("nonnumeric port: '%s'" % host[i+1:])
httplib.InvalidURL: nonnumeric port: 'port/'
Error in sys.excepthook:
Traceback (most recent call last):
File "/usr/lib/python2.7/dist-packages/apport_python_hook.py", line 70, in apport_excepthook
binary = os.path.realpath(os.path.join(os.getcwdu(), sys.argv[0]))
File "/usr/lib/python2.7/posixpath.py", line 71, in join
path += '/' + b
UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 15: ordinal not in range(128)
Original exception was:
Traceback (most recent call last):
File "WebServiceAusführen.py", line 5, in <module>
f = urllib2.urlopen('http://www.python.org/')
File "/usr/lib/python2.7/urllib2.py", line 126, in urlopen
return _opener.open(url, data, timeout)
File "/usr/lib/python2.7/urllib2.py", line 400, in open
response = self._open(req, data)
File "/usr/lib/python2.7/urllib2.py", line 418, in _open
'_open', req)
File "/usr/lib/python2.7/urllib2.py", line 378, in _call_chain
result = func(*args)
File "/usr/lib/python2.7/urllib2.py", line 1207, in http_open
return self.do_open(httplib.HTTPConnection, req)
File "/usr/lib/python2.7/urllib2.py", line 1146, in do_open
h = http_class(host, timeout=req.timeout) # will parse host:port
File "/usr/lib/python2.7/httplib.py", line 693, in __init__
self._set_hostport(host, port)
File "/usr/lib/python2.7/httplib.py", line 721, in _set_hostport
raise InvalidURL("nonnumeric port: '%s'" % host[i+1:])
httplib.InvalidURL: nonnumeric port: 'port/'
help would be pretty awesome because I really don't know how to make such a big error in such a small program!
The exception is thrown because you have a faulty proxy configuration.
On POSIX systems, the library looks for *_proxy environment variables (upper and lowercase). For a HTTP URL, that's the http_proxy environment variable.
You can verify this by looking for proxy variables:
import os
print {k: v for k, v in os.environ.items() if k.lower().endswith('_proxy')}
Whatever value you have configured on your system is not a valid hostname and port combination and Python is choking on that.
I'm using this code to get the web site html content,
import urllib.request
import lxml.html as lh
req= urllib.request.Request("http://www.ip-adress.com/ip_tracer/157.123.22.11",
headers={'User-Agent' : "Magic Browser"})
html = urllib.request.urlopen(req).read()
doc = lh.fromstring(html)
print (''.join(doc.xpath('.//*[#class="odd"]')[-1].text_content().split()))
I want to get the Organization: Zenith Data Systems.
but it shows some errors
Traceback (most recent call last):
File "/usr/local/python3.2.3/lib/python3.2/urllib/request.py", line 1135, in do_open
h.request(req.get_method(), req.selector, req.data, headers)
File "/usr/local/python3.2.3/lib/python3.2/http/client.py", line 967, in request
self._send_request(method, url, body, headers)
File "/usr/local/python3.2.3/lib/python3.2/http/client.py", line 1005, in _send_request
self.endheaders(body)
File "/usr/local/python3.2.3/lib/python3.2/http/client.py", line 963, in endheaders
self._send_output(message_body)
File "/usr/local/python3.2.3/lib/python3.2/http/client.py", line 808, in _send_output
self.send(msg)
File "/usr/local/python3.2.3/lib/python3.2/http/client.py", line 746, in send
self.connect()
File "/usr/local/python3.2.3/lib/python3.2/http/client.py", line 724, in connect
self.timeout, self.source_address)
File "/usr/local/python3.2.3/lib/python3.2/socket.py", line 404, in create_connection
raise err
File "/usr/local/python3.2.3/lib/python3.2/socket.py", line 395, in create_connection
sock.connect(sa)
socket.error: [Errno 111] Connection refused
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "ext.py", line 4, in <module>
html = urllib.request.urlopen(req).read()
File "/usr/local/python3.2.3/lib/python3.2/urllib/request.py", line 138, in urlopen
return opener.open(url, data, timeout)
File "/usr/local/python3.2.3/lib/python3.2/urllib/request.py", line 369, in open
response = self._open(req, data)
File "/usr/local/python3.2.3/lib/python3.2/urllib/request.py", line 387, in _open
'_open', req)
File "/usr/local/python3.2.3/lib/python3.2/urllib/request.py", line 347, in _call_chain
result = func(*args)
File "/usr/local/python3.2.3/lib/python3.2/urllib/request.py", line 1155, in http_open
return self.do_open(http.client.HTTPConnection, req)
File "/usr/local/python3.2.3/lib/python3.2/urllib/request.py", line 1138, in do_open
raise URLError(err)
urllib.error.URLError: <urlopen error [Errno 111] Connection refused>}
How to solve it. Thanks,
Basically, Connection Refused means only registered users are allowed to access the page, or server under heavy maintenance or similar reasons.
From your above code, if you want to handle errors you may try using try and except like below code:
try:
req= urllib.request.Request("http://www.ip-adress.com/ip_tracer/157.123.22.11",headers={'User-Agent' : "Magic Browser"})
html = urllib.request.urlopen(req).read()
doc = lh.fromstring(html)
print (''.join(doc.xpath('.//*[#class="odd"]')[-1].text_content().split()))
except urllib.error.URLError as e:
print(e.reason)
For some reason I can get this to work, using single proxy everything seems fine.
#This works
import socks
import urllib2
socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, '68.xx.193.xx', 666)
socks.wrapmodule(urllib2)
print urllib2.urlopen('http://automation.whatismyip.com/n09230945.asp').read()
&
#This doesn't
import socks
import urllib2
proxies=['68.xx.193.xx','xx.178.xx.70','98.xx.84.xx','83.xx.86.xx']
ports=[666,1080,859,910]
for i in range(len(proxies)):
socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, repr(proxies[i]), ports[i])
socks.wrapmodule(urllib2)
print urllib2.urlopen('http://automation.whatismyip.com/n09230945.asp').read()
Error:
Traceback (most recent call last):
File "/home/zer0/Aptana Studio 3 Workspace/sy/src/test.py", line 38, in <module>
print urllib2.urlopen('http://automation.whatismyip.com/n09230945.asp').read()
File "/usr/lib/python2.7/urllib2.py", line 126, in urlopen
return _opener.open(url, data, timeout)
File "/usr/lib/python2.7/urllib2.py", line 391, in open
response = self._open(req, data)
File "/usr/lib/python2.7/urllib2.py", line 409, in _open
'_open', req)
File "/usr/lib/python2.7/urllib2.py", line 369, in _call_chain
result = func(*args)
File "/usr/lib/python2.7/urllib2.py", line 1185, in http_open
return self.do_open(httplib.HTTPConnection, req)
File "/usr/lib/python2.7/urllib2.py", line 1160, in do_open
raise URLError(err)
urllib2.URLError: <urlopen error [Errno -5] No address associated with hostname>
Run this:
proxies=['68.xx.193.xx','xx.178.xx.70','98.xx.84.xx','83.xx.86.xx']
ports=[666,1080,859,910]
for i in range(len(proxies)):
print (repr(proxies[i]), ports[i])
You'll get
("'68.xx.193.xx'", 666)
("'xx.178.xx.70'", 1080)
("'98.xx.84.xx'", 859)
("'83.xx.86.xx'", 910)
You're adding quotes you don't want with the repr call, so urllib2 thinks it's a hostname instead of an IP address. Get rid of it and you should be fine.