Fix infoQ in Python3

This commit is contained in:
Philipp Hagemeister 2013-01-01 21:07:37 +01:00
parent 511eda8eda
commit 4fcca4bb18

View File

@ -3,6 +3,7 @@
from __future__ import absolute_import from __future__ import absolute_import
import base64
import datetime import datetime
import netrc import netrc
import os import os
@ -2824,10 +2825,6 @@ class InfoQIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$' _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
IE_NAME = u'infoq' IE_NAME = u'infoq'
def report_webpage(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
def report_extraction(self, video_id): def report_extraction(self, video_id):
"""Report information extraction.""" """Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
@ -2838,38 +2835,29 @@ class InfoQIE(InfoExtractor):
self._downloader.trouble(u'ERROR: invalid URL: %s' % url) self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return return
self.report_webpage(url) webpage = self._download_webpage(url, video_id=url)
request = compat_urllib_request.Request(url)
try:
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
return
self.report_extraction(url) self.report_extraction(url)
# Extract video URL # Extract video URL
mobj = re.search(r"jsclassref='([^']*)'", webpage) mobj = re.search(r"jsclassref='([^']*)'", webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video url') self._downloader.trouble(u'ERROR: unable to extract video url')
return return
video_url = 'rtmpe://video.infoq.com/cfx/st/' + compat_urllib_parse.unquote(mobj.group(1).decode('base64')) real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
# Extract title # Extract title
mobj = re.search(r'contentTitle = "(.*?)";', webpage) mobj = re.search(r'contentTitle = "(.*?)";', webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video title') self._downloader.trouble(u'ERROR: unable to extract video title')
return return
video_title = mobj.group(1).decode('utf-8') video_title = mobj.group(1)
# Extract description # Extract description
video_description = u'No description available.' video_description = u'No description available.'
mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage) mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage)
if mobj is not None: if mobj is not None:
video_description = mobj.group(1).decode('utf-8') video_description = mobj.group(1)
video_filename = video_url.split('/')[-1] video_filename = video_url.split('/')[-1]
video_id, extension = video_filename.split('.') video_id, extension = video_filename.split('.')