commit d93e4dcbb7fb68666528e251623b90d832d9cffc
parent 73e79f2a1be3179edd8eebf4b7b6d56fe953a4a8
Author: Philipp Hagemeister <phihag@phihag.de>
Date: Mon, 8 Jul 2013 01:15:19 +0200
Merge branch 'master' of github.com:rg3/youtube-dl
Diffstat:
3 files changed, 64 insertions(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
@@ -3,6 +3,7 @@ import os
import re
import socket
import sys
+import netrc
from ..utils import (
compat_http_client,
@@ -163,6 +164,10 @@ class InfoExtractor(object):
"""Report attempt to confirm age."""
self.to_screen(u'Confirming age')
+ def report_login(self):
+ """Report attempt to log in."""
+ self.to_screen(u'Logging in')
+
#Methods for following #608
#They set the correct value of the '_type' key
def video_result(self, video_info):
@@ -227,6 +232,36 @@ class InfoExtractor(object):
else:
return res
+ def _get_login_info(self):
+ """
+ Get the the login info as (username, password)
+ It will look in the netrc file using the _NETRC_MACHINE value
+ If there's no info available, return (None, None)
+ """
+ if self._downloader is None:
+ return (None, None)
+
+ username = None
+ password = None
+ downloader_params = self._downloader.params
+
+ # Attempt to use provided username and password or .netrc data
+ if downloader_params.get('username', None) is not None:
+ username = downloader_params['username']
+ password = downloader_params['password']
+ elif downloader_params.get('usenetrc', False):
+ try:
+ info = netrc.netrc().authenticators(self._NETRC_MACHINE)
+ if info is not None:
+ username = info[0]
+ password = info[2]
+ else:
+ raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
+ except (IOError, netrc.NetrcParseError) as err:
+ self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
+
+ return (username, password)
+
class SearchInfoExtractor(InfoExtractor):
"""
Base class for paged search queries extractors.
diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
@@ -17,6 +17,7 @@ class VimeoIE(InfoExtractor):
# _VALID_URL matches Vimeo URLs
_VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)(?:[?].*)?$'
+ _NETRC_MACHINE = 'vimeo'
IE_NAME = u'vimeo'
_TEST = {
u'url': u'http://vimeo.com/56015672',
@@ -31,6 +32,25 @@ class VimeoIE(InfoExtractor):
}
}
+ def _login(self):
+ (username, password) = self._get_login_info()
+ if username is None:
+ return
+ self.report_login()
+ login_url = 'https://vimeo.com/log_in'
+ webpage = self._download_webpage(login_url, None, False)
+ token = re.search(r'xsrft: \'(.*?)\'', webpage).group(1)
+ data = compat_urllib_parse.urlencode({'email': username,
+ 'password': password,
+ 'action': 'login',
+ 'service': 'vimeo',
+ 'token': token,
+ })
+ login_request = compat_urllib_request.Request(login_url, data)
+ login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+ login_request.add_header('Cookie', 'xsrft=%s' % token)
+ self._download_webpage(login_request, None, False, u'Wrong login info')
+
def _verify_video_password(self, url, video_id, webpage):
password = self._downloader.params.get('videopassword', None)
if password is None:
@@ -50,6 +70,9 @@ class VimeoIE(InfoExtractor):
u'Verifying the password',
u'Wrong password')
+ def _real_initialize(self):
+ self._login()
+
def _real_extract(self, url, new_video=True):
# Extract ID from URL
mobj = re.match(self._VALID_URL, url)
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
@@ -473,7 +473,12 @@ class YoutubeIE(InfoExtractor):
video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
# thumbnail image
- if 'thumbnail_url' not in video_info:
+ # We try first to get a high quality image:
+ m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
+ video_webpage, re.DOTALL)
+ if m_thumb is not None:
+ video_thumbnail = m_thumb.group(1)
+ elif 'thumbnail_url' not in video_info:
self._downloader.report_warning(u'unable to extract video thumbnail')
video_thumbnail = ''
else: # don't panic if we can't find it
