Merge tag 'upstream/2013.08.08'

[youtubedl] / youtube_dl / extractor / vimeo.py

diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
index 20dc255d4c3e8de8dd4dd4cc30a60cb0427135de..cc9c8d0188749761b79b90652d3c0c843a24eda3 100644 (file)
--- a/youtube_dl/extractor/vimeo.py
+++ b/youtube_dl/extractor/vimeo.py
@@ -1,5 +1,6 @@
 import json
 import re
 import json
 import re

+import itertools

 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (


@@ -16,8 +17,40 @@ class VimeoIE(InfoExtractor):
     """Information extractor for vimeo.com."""
 
     # _VALID_URL matches Vimeo URLs
     """Information extractor for vimeo.com."""
 
     # _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]+)'
+    _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'
     IE_NAME = u'vimeo'

+    _TEST = {
+        u'url': u'http://vimeo.com/56015672',
+        u'file': u'56015672.mp4',
+        u'md5': u'8879b6cc097e987f02484baf890129e5',
+        u'info_dict': {
+            u"upload_date": u"20121220", 
+            u"description": u"This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", 
+            u"uploader_id": u"user7108434", 
+            u"uploader": u"Filippo Valsorda", 
+            u"title": u"youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550"
+        }
+    }
+
+    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)
 
     def _verify_video_password(self, url, video_id, webpage):
         password = self._downloader.params.get('videopassword', None)


@@ -38,6 +71,9 @@ class VimeoIE(InfoExtractor):
                                u'Verifying the password',
                                u'Wrong password')
 
                                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)
     def _real_extract(self, url, new_video=True):
         # Extract ID from URL
         mobj = re.match(self._VALID_URL, url)


@@ -136,3 +172,31 @@ class VimeoIE(InfoExtractor):
             'thumbnail':    video_thumbnail,
             'description':  video_description,
         }]
             'thumbnail':    video_thumbnail,
             'description':  video_description,
         }]

+
+
+class VimeoChannelIE(InfoExtractor):
+    IE_NAME = u'vimeo:channel'
+    _VALID_URL = r'(?:https?://)?vimeo.\com/channels/(?P<id>[^/]+)'
+    _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        channel_id =  mobj.group('id')
+        video_ids = []
+
+        for pagenum in itertools.count(1):
+            webpage = self._download_webpage('http://vimeo.com/channels/%s/videos/page:%d' % (channel_id, pagenum),
+                                             channel_id, u'Downloading page %s' % pagenum)
+            video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
+            if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
+                break
+
+        entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
+                   for video_id in video_ids]
+        channel_title = self._html_search_regex(r'<a href="/channels/%s">(.*?)</a>' % channel_id,
+                                                webpage, u'channel title')
+        return {'_type': 'playlist',
+                'id': channel_id,
+                'title': channel_title,
+                'entries': entries,
+                }