debian/control: Update list of extractors.

[youtubedl] / youtube_dl / extractor / vimeo.py

diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
index 1125513c7b0cd443becb2847acb9db9032303dfb..f27763ae2ff110051613243ef2543e3349d6b019 100644 (file)
--- a/youtube_dl/extractor/vimeo.py
+++ b/youtube_dl/extractor/vimeo.py
@@ -1,3 +1,4 @@
+# encoding: utf-8

 import json
 import re
 import itertools
 import json
 import re
 import itertools


@@ -10,6 +11,7 @@ from ..utils import (
     clean_html,
     get_element_by_attribute,
     ExtractorError,
     clean_html,
     get_element_by_attribute,
     ExtractorError,

+    RegexNotFoundError,

     std_headers,
     unsmuggle_url,
 )
     std_headers,
     unsmuggle_url,
 )


@@ -18,12 +20,12 @@ 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]+)/?(?:[?].*)?$'
+    _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|(?P<player>player))\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$'

     _NETRC_MACHINE = 'vimeo'
     IE_NAME = u'vimeo'
     _TESTS = [
         {
     _NETRC_MACHINE = 'vimeo'
     IE_NAME = u'vimeo'
     _TESTS = [
         {

-            u'url': u'http://vimeo.com/56015672',
+            u'url': u'http://vimeo.com/56015672#at=0',

             u'file': u'56015672.mp4',
             u'md5': u'8879b6cc097e987f02484baf890129e5',
             u'info_dict': {
             u'file': u'56015672.mp4',
             u'md5': u'8879b6cc097e987f02484baf890129e5',
             u'info_dict': {


@@ -54,7 +56,22 @@ class VimeoIE(InfoExtractor):
                 u'title': u'Kathy Sierra: Building the minimum Badass User, Business of Software',
                 u'uploader': u'The BLN & Business of Software',
             },
                 u'title': u'Kathy Sierra: Building the minimum Badass User, Business of Software',
                 u'uploader': u'The BLN & Business of Software',
             },

-        }
+        },
+        {
+            u'url': u'http://vimeo.com/68375962',
+            u'file': u'68375962.mp4',
+            u'md5': u'aaf896bdb7ddd6476df50007a0ac0ae7',
+            u'note': u'Video protected with password',
+            u'info_dict': {
+                u'title': u'youtube-dl password protected test video',
+                u'upload_date': u'20130614',
+                u'uploader_id': u'user18948128',
+                u'uploader': u'Jaime Marquínez Ferrándiz',
+            },
+            u'params': {
+                u'videopassword': u'youtube-dl',
+            },
+        },

     ]
 
     def _login(self):
     ]
 
     def _login(self):


@@ -111,11 +128,9 @@ class VimeoIE(InfoExtractor):
             raise ExtractorError(u'Invalid URL: %s' % url)
 
         video_id = mobj.group('id')
             raise ExtractorError(u'Invalid URL: %s' % url)
 
         video_id = mobj.group('id')

-        if not mobj.group('proto'):
-            url = 'https://' + url
-        elif mobj.group('pro'):
+        if mobj.group('pro') or mobj.group('player'):

             url = 'http://player.vimeo.com/video/' + video_id
             url = 'http://player.vimeo.com/video/' + video_id

-        elif mobj.group('direct_link'):
+        else:

             url = 'https://vimeo.com/' + video_id
 
         # Retrieve video webpage to extract further information
             url = 'https://vimeo.com/' + video_id
 
         # Retrieve video webpage to extract further information


@@ -129,18 +144,26 @@ class VimeoIE(InfoExtractor):
 
         # Extract the config JSON
         try:
 
         # Extract the config JSON
         try:

-            config = self._search_regex([r' = {config:({.+?}),assets:', r'c=({.+?);'],
-                webpage, u'info section', flags=re.DOTALL)
-            config = json.loads(config)
-        except:
+            try:
+                config_url = self._html_search_regex(
+                    r' data-config-url="(.+?)"', webpage, u'config URL')
+                config_json = self._download_webpage(config_url, video_id)
+                config = json.loads(config_json)
+            except RegexNotFoundError:
+                # For pro videos or player.vimeo.com urls
+                config = self._search_regex([r' = {config:({.+?}),assets:', r'(?:c|b)=({.+?});'],
+                    webpage, u'info section', flags=re.DOTALL)
+                config = json.loads(config)
+        except Exception as e:

             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
                 raise ExtractorError(u'The author has restricted the access to this video, try with the "--referer" option')
 
             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
                 raise ExtractorError(u'The author has restricted the access to this video, try with the "--referer" option')
 

-            if re.search('If so please provide the correct password.', webpage):
+            if re.search('<form[^>]+?id="pw_form"', webpage) is not None:

                 self._verify_video_password(url, video_id, webpage)
                 return self._real_extract(url)
             else:
                 self._verify_video_password(url, video_id, webpage)
                 return self._real_extract(url)
             else:

-                raise ExtractorError(u'Unable to extract info section')
+                raise ExtractorError(u'Unable to extract info section',
+                                     cause=e)

 
         # Extract title
         video_title = config["video"]["title"]
 
         # Extract title
         video_title = config["video"]["title"]


@@ -180,7 +203,7 @@ class VimeoIE(InfoExtractor):
         # Vimeo specific: extract video codec and quality information
         # First consider quality, then codecs, then take everything
         codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]
         # Vimeo specific: extract video codec and quality information
         # First consider quality, then codecs, then take everything
         codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]

-        files = { 'hd': [], 'sd': [], 'other': []}
+        files = {'hd': [], 'sd': [], 'other': []}

         config_files = config["video"].get("files") or config["request"].get("files")
         for codec_name, codec_extension in codecs:
             for quality in config_files.get(codec_name, []):
         config_files = config["video"].get("files") or config["request"].get("files")
         for codec_name, codec_extension in codecs:
             for quality in config_files.get(codec_name, []):


@@ -209,7 +232,7 @@ class VimeoIE(InfoExtractor):
         if len(formats) == 0:
             raise ExtractorError(u'No known codec found')
 
         if len(formats) == 0:
             raise ExtractorError(u'No known codec found')
 

-        return [{
+        return {

             'id':       video_id,
             'uploader': video_uploader,
             'uploader_id': video_uploader_id,
             'id':       video_id,
             'uploader': video_uploader,
             'uploader_id': video_uploader_id,


@@ -218,32 +241,54 @@ class VimeoIE(InfoExtractor):
             'thumbnail':    video_thumbnail,
             'description':  video_description,
             'formats': formats,
             'thumbnail':    video_thumbnail,
             'description':  video_description,
             'formats': formats,

-        }]
+            'webpage_url': url,
+        }

 
 
 class VimeoChannelIE(InfoExtractor):
     IE_NAME = u'vimeo:channel'
     _VALID_URL = r'(?:https?://)?vimeo.\com/channels/(?P<id>[^/]+)'
     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 
 
 class VimeoChannelIE(InfoExtractor):
     IE_NAME = u'vimeo:channel'
     _VALID_URL = r'(?:https?://)?vimeo.\com/channels/(?P<id>[^/]+)'
     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'

+    _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'

 
 

-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        channel_id =  mobj.group('id')
+    def _extract_videos(self, list_id, base_url):

         video_ids = []
         video_ids = []

-

         for pagenum in itertools.count(1):
         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)
+            webpage = self._download_webpage(
+                '%s/videos/page:%d/' % (base_url, pagenum),list_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]
             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')
+        list_title = self._html_search_regex(self._TITLE_RE, webpage,
+            u'list title')

         return {'_type': 'playlist',
         return {'_type': 'playlist',

-                'id': channel_id,
-                'title': channel_title,
+                'id': list_id,
+                'title': list_title,

                 'entries': entries,
                 }
                 'entries': entries,
                 }

+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        channel_id =  mobj.group('id')
+        return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id)
+
+
+class VimeoUserIE(VimeoChannelIE):
+    IE_NAME = u'vimeo:user'
+    _VALID_URL = r'(?:https?://)?vimeo.\com/(?P<name>[^/]+)'
+    _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
+
+    @classmethod
+    def suitable(cls, url):
+        if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url):
+            return False
+        return super(VimeoUserIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        name = mobj.group('name')
+        return self._extract_videos(name, 'http://vimeo.com/%s' % name)