release 2014.02.21

Fix minor typo: “to to” → “to”.

README.md

@@ -20,7 +20,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      sure that you have sufficient permissions
                                      (run with sudo if needed)
     -i, --ignore-errors              continue on download errors, for example to
-                                     to skip unavailable videos in a playlist
+                                     skip unavailable videos in a playlist
     --abort-on-error                 Abort downloading of further videos (in the
                                      playlist or the command line) if an error
                                      occurs
@@ -246,7 +246,7 @@ which means you can modify it, redistribute it or use it however you like.
 
 # CONFIGURATION
 
-You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl.conf`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
+You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
 
 # OUTPUT TEMPLATE
 
@@ -357,7 +357,7 @@ If you want to create a build of youtube-dl yourself, you'll need
 
 ### Adding support for a new site
 
-If you want to add support for a new site, copy *any* [recently modified](https://github.com/rg3/youtube-dl/commits/master/youtube_dl/extractor) file in `youtube_dl/extractor`, add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Don't forget to run the tests with `python test/test_download.py Test_Download.test_YourExtractor`! For a detailed tutorial, refer to [this blog post](http://filippo.io/add-support-for-a-new-video-site-to-youtube-dl/).
+If you want to add support for a new site, copy *any* [recently modified](https://github.com/rg3/youtube-dl/commits/master/youtube_dl/extractor) file in `youtube_dl/extractor`, add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Don't forget to run the tests with `python test/test_download.py TestDownload.test_YourExtractor`! For a detailed tutorial, refer to [this blog post](http://filippo.io/add-support-for-a-new-video-site-to-youtube-dl/).
 
 # BUGS
 

test/test_playlists.py

@@ -250,5 +250,14 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['title'], 'python language')
         self.assertTrue(len(result['entries']) == 15)
 
+    def test_generic_rss_feed(self):
+        dl = FakeYDL()
+        ie = GenericIE(dl)
+        result = ie.extract('http://www.escapistmagazine.com/rss/videos/list/1.xml')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'http://www.escapistmagazine.com/rss/videos/list/1.xml')
+        self.assertEqual(result['title'], 'Zero Punctuation')
+        self.assertTrue(len(result['entries']) > 10)
+
 if __name__ == '__main__':
     unittest.main()

youtube_dl/__init__.py

@@ -208,7 +208,7 @@ def parseOpts(overrideArguments=None):
     general.add_option('-U', '--update',
             action='store_true', dest='update_self', help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
     general.add_option('-i', '--ignore-errors',
-            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to to skip unavailable videos in a playlist', default=False)
+            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to skip unavailable videos in a playlist', default=False)
     general.add_option('--abort-on-error',
             action='store_false', dest='ignoreerrors',
             help='Abort downloading of further videos (in the playlist or the command line) if an error occurs')

youtube_dl/extractor/bbccouk.py

@@ -162,6 +162,11 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         group_id = mobj.group('id')
 
+        webpage = self._download_webpage(url, group_id, 'Downloading video page')
+        if re.search(r'id="emp-error" class="notinuk">', webpage):
+            raise ExtractorError('Currently BBC iPlayer TV programmes are available to play in the UK only',
+                expected=True)
+
         playlist = self._download_xml('http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, group_id,
             'Downloading playlist XML')
 

youtube_dl/extractor/generic.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 
 import os
 import re
+import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from .youtube import YoutubeIE
@@ -159,6 +160,25 @@ class GenericIE(InfoExtractor):
             raise ExtractorError('Invalid URL protocol')
         return response
 
+    def _extract_rss(self, url, video_id, doc):
+        playlist_title = doc.find('./channel/title').text
+        playlist_desc_el = doc.find('./channel/description')
+        playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
+
+        entries = [{
+            '_type': 'url',
+            'url': e.find('link').text,
+            'title': e.find('title').text,
+        } for e in doc.findall('./channel/item')]
+
+        return {
+            '_type': 'playlist',
+            'id': url,
+            'title': playlist_title,
+            'description': playlist_desc,
+            'entries': entries,
+        }
+
     def _real_extract(self, url):
         parsed_url = compat_urlparse.urlparse(url)
         if not parsed_url.scheme:
@@ -219,6 +239,14 @@ class GenericIE(InfoExtractor):
 
         self.report_extraction(video_id)
 
+        # Is it an RSS feed?
+        try:
+            doc = xml.etree.ElementTree.fromstring(webpage)
+            if doc.tag == 'rss':
+                return self._extract_rss(url, video_id, doc)
+        except xml.etree.ElementTree.ParseError:
+            pass
+
         # it's tempting to parse this further, but you would
         # have to take into account all the variations like
         #   Video Title - Site Name

youtube_dl/extractor/liveleak.py

@@ -4,15 +4,17 @@ import json
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class LiveLeakIE(InfoExtractor):
     _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
     _TESTS = [{
         'url': 'http://www.liveleak.com/view?i=757_1364311680',
-        'file': '757_1364311680.mp4',
         'md5': '0813c2430bea7a46bf13acf3406992f4',
         'info_dict': {
+            'id': '757_1364311680',
+            'ext': 'mp4',
             'description': 'extremely bad day for this guy..!',
             'uploader': 'ljfriel2',
             'title': 'Most unlucky car accident'
@@ -20,25 +22,62 @@ class LiveLeakIE(InfoExtractor):
     },
     {
         'url': 'http://www.liveleak.com/view?i=f93_1390833151',
-        'file': 'f93_1390833151.mp4',
         'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
         'info_dict': {
+            'id': 'f93_1390833151',
+            'ext': 'mp4',
             'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
             'uploader': 'ARD_Stinkt',
             'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
         }
+    },
+    {
+        'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
+        'md5': '42c6d97d54f1db107958760788c5f48f',
+        'info_dict': {
+            'id': '4f7_1392687779',
+            'ext': 'mp4',
+            'description': "The guy with the cigarette seems amazingly nonchalant about the whole thing...  I really hope my friends' reactions would be a bit stronger.\r\n\r\nAction-go to 0:55.",
+            'uploader': 'CapObveus',
+            'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
+            'age_limit': 18,
+        }
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-
         video_id = mobj.group('video_id')
         webpage = self._download_webpage(url, video_id)
+
+        video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
+        video_description = self._og_search_description(webpage)
+        video_uploader = self._html_search_regex(
+            r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
+        age_limit = int_or_none(self._search_regex(
+            r'you confirm that you are ([0-9]+) years and over.',
+            webpage, 'age limit', default=None))
+
         sources_raw = self._search_regex(
             r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
         if sources_raw is None:
-            sources_raw = '[{ %s}]' % (
-                self._search_regex(r'(file: ".*?"),', webpage, 'video URL'))
+            alt_source = self._search_regex(
+                r'(file: ".*?"),', webpage, 'video URL', default=None)
+            if alt_source:
+                sources_raw = '[{ %s}]' % alt_source
+            else:
+                # Maybe an embed?
+                embed_url = self._search_regex(
+                    r'<iframe[^>]+src="(http://www.prochan.com/embed\?[^"]+)"',
+                    webpage, 'embed URL')
+                return {
+                    '_type': 'url_transparent',
+                    'url': embed_url,
+                    'id': video_id,
+                    'title': video_title,
+                    'description': video_description,
+                    'uploader': video_uploader,
+                    'age_limit': age_limit,
+                }
 
         sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
         sources = json.loads(sources_json)
@@ -49,15 +88,11 @@ class LiveLeakIE(InfoExtractor):
         } for s in sources]
         self._sort_formats(formats)
 
-        video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
-        video_description = self._og_search_description(webpage)
-        video_uploader = self._html_search_regex(
-            r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
-
         return {
             'id': video_id,
             'title': video_title,
             'description': video_description,
             'uploader': video_uploader,
             'formats': formats,
+            'age_limit': age_limit,
         }

youtube_dl/extractor/wimp.py

@@ -6,14 +6,15 @@ from .common import InfoExtractor
 
 
 class WimpIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?wimp\.com/([^/]+)/'
+    _VALID_URL = r'http://(?:www\.)?wimp\.com/([^/]+)/'
     _TEST = {
-        'url': 'http://www.wimp.com/deerfence/',
-        'file': 'deerfence.flv',
-        'md5': '8b215e2e0168c6081a1cf84b2846a2b5',
+        'url': 'http://www.wimp.com/maruexhausted/',
+        'md5': 'f1acced123ecb28d9bb79f2479f2b6a1',
         'info_dict': {
-            "title": "Watch Till End: Herd of deer jump over a fence.",
-            "description": "These deer look as fluid as running water when they jump over this fence as a herd. This video is one that needs to be watched until the very end for the true majesty to be witnessed, but once it comes, it's sure to take your breath away.",
+            'id': 'maruexhausted',
+            'ext': 'flv',
+            'title': 'Maru is exhausted.',
+            'description': 'md5:57e099e857c0a4ea312542b684a869b8',
         }
     }
 
@@ -30,4 +31,4 @@ class WimpIE(InfoExtractor):
             'title': self._og_search_title(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
             'description': self._og_search_description(webpage),
-        }
+        }

youtube_dl/extractor/xhamster.py

@@ -4,51 +4,51 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_urllib_parse,
     ExtractorError,
+    unified_strdate,
+    str_to_int,
+    int_or_none,
+    parse_duration,
 )
 
 
 class XHamsterIE(InfoExtractor):
     """Information Extractor for xHamster"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
-    _TESTS = [{
-        'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
-        'file': '1509445.mp4',
-        'md5': '8281348b8d3c53d39fffb377d24eac4e',
-        'info_dict': {
-            "upload_date": "20121014",
-            "uploader_id": "Ruseful2011",
-            "title": "FemaleAgent Shy beauty takes the bait",
-            "age_limit": 18,
+    _VALID_URL = r'http://(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
+    _TESTS = [
+        {
+            'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
+            'md5': '8281348b8d3c53d39fffb377d24eac4e',
+            'info_dict': {
+                'id': '1509445',
+                'ext': 'mp4',
+                'title': 'FemaleAgent Shy beauty takes the bait',
+                'upload_date': '20121014',
+                'uploader_id': 'Ruseful2011',
+                'duration': 893,
+                'age_limit': 18,
+            }
+        },
+        {
+            'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
+            'md5': '4cbd8d56708ecb4fb4124c23e4acb81a',
+            'info_dict': {
+                'id': '2221348',
+                'ext': 'mp4',
+                'title': 'Britney Spears  Sexy Booty',
+                'upload_date': '20130914',
+                'uploader_id': 'jojo747400',
+                'duration': 200,
+                'age_limit': 18,
+            }
         }
-    },
-    {
-        'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
-        'file': '2221348.flv',
-        'md5': 'e767b9475de189320f691f49c679c4c7',
-        'info_dict': {
-            "upload_date": "20130914",
-            "uploader_id": "jojo747400",
-            "title": "Britney Spears  Sexy Booty",
-            "age_limit": 18,
-        }
-    }]
+    ]
 
     def _real_extract(self,url):
         def extract_video_url(webpage):
-            mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
-            if mobj is None:
-                raise ExtractorError('Unable to extract media URL')
-            if len(mobj.group('server')) == 0:
-                return compat_urllib_parse.unquote(mobj.group('file'))
-            else:
-                return mobj.group('server')+'/key='+mobj.group('file')
-
-        def extract_mp4_video_url(webpage):
-            mp4 = re.search(r'<a href=\"(.+?)\" class=\"mp4Play\"',webpage)
+            mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage)
             if mp4 is None:
-                return None
+                raise ExtractorError('Unable to extract media URL')
             else:
                 return mp4.group(1)
 
@@ -62,50 +62,48 @@ class XHamsterIE(InfoExtractor):
         mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
         webpage = self._download_webpage(mrss_url, video_id)
 
-        video_title = self._html_search_regex(
-            r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
+        title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
 
         # Only a few videos have an description
         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
-        video_description = mobj.group(1) if mobj else None
+        description = mobj.group(1) if mobj else None
 
-        mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
-        if mobj:
-            video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
-        else:
-            video_upload_date = None
-            self._downloader.report_warning('Unable to extract upload date')
+        upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
+            webpage, 'upload date', fatal=False)
+        if upload_date:
+            upload_date = unified_strdate(upload_date)
 
-        video_uploader_id = self._html_search_regex(
-            r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
+        uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
             webpage, 'uploader id', default='anonymous')
 
-        video_thumbnail = self._search_regex(
-            r'\'image\':\'(?P<thumbnail>[^\']+)\'',
-            webpage, 'thumbnail', fatal=False)
+        thumbnail = self._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False)
+
+        duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
+            webpage, 'duration', fatal=False))
+
+        view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
+        if view_count:
+            view_count = str_to_int(view_count)
+
+        mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
+        (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
+
+        mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
+        comment_count = mobj.group('commentcount') if mobj else 0
 
         age_limit = self._rta_search(webpage)
 
         hd = is_hd(webpage)
+
         video_url = extract_video_url(webpage)
         formats = [{
             'url': video_url,
             'format_id': 'hd' if hd else 'sd',
-            'preference': 0,
+            'preference': 1,
         }]
 
-        video_mp4_url = extract_mp4_video_url(webpage)
-        if video_mp4_url is not None:
-            formats.append({
-                'url': video_mp4_url,
-                'ext': 'mp4',
-                'format_id': 'mp4-hd' if hd else 'mp4-sd',
-                'preference': 1,
-            })
-
         if not hd:
-            webpage = self._download_webpage(
-                mrss_url + '?hd', video_id, note='Downloading HD webpage')
+            webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
             if is_hd(webpage):
                 video_url = extract_video_url(webpage)
                 formats.append({
@@ -118,11 +116,16 @@ class XHamsterIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': video_title,
-            'formats': formats,
-            'description': video_description,
-            'upload_date': video_upload_date,
-            'uploader_id': video_uploader_id,
-            'thumbnail': video_thumbnail,
+            'title': title,
+            'description': description,
+            'upload_date': upload_date,
+            'uploader_id': uploader_id,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'view_count': view_count,
+            'like_count': int_or_none(like_count),
+            'dislike_count': int_or_none(dislike_count),
+            'comment_count': int_or_none(comment_count),
             'age_limit': age_limit,
+            'formats': formats,
         }

youtube_dl/extractor/youtube.py

@@ -1443,9 +1443,9 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
                      |
                         ((?:PL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,})
                      )"""
-    _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&page=%s'
+    _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
     _MORE_PAGES_INDICATOR = r'data-link-type="next"'
-    _VIDEO_RE = r'href="/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)'
+    _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)'
     IE_NAME = u'youtube:playlist'
 
     def _real_initialize(self):
@@ -1493,29 +1493,31 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
             raise ExtractorError(u'For downloading YouTube.com top lists, use '
                 u'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True)
 
+        url = self._TEMPLATE_URL % playlist_id
+        page = self._download_webpage(url, playlist_id)
+        more_widget_html = content_html = page
+
         # Extract the video ids from the playlist pages
         ids = []
 
         for page_num in itertools.count(1):
-            url = self._TEMPLATE_URL % (playlist_id, page_num)
-            page = self._download_webpage(url, playlist_id, u'Downloading page #%s' % page_num)
-            matches = re.finditer(self._VIDEO_RE, page)
+            matches = re.finditer(self._VIDEO_RE, content_html)
             # We remove the duplicates and the link with index 0
             # (it's not the first video of the playlist)
             new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0')
             ids.extend(new_ids)
 
-            if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+            mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
+            if not mobj:
                 break
 
-        try:
-            playlist_title = self._og_search_title(page)
-        except RegexNotFoundError:
-            self.report_warning(
-                u'Playlist page is missing OpenGraph title, falling back ...',
-                playlist_id)
-            playlist_title = self._html_search_regex(
-                r'<h1 class="pl-header-title">(.*?)</h1>', page, u'title')
+            more = self._download_json(
+                'https://youtube.com/%s' % mobj.group('more'), playlist_id, 'Downloading page #%s' % page_num)
+            content_html = more['content_html']
+            more_widget_html = more['load_more_widget_html']
+
+        playlist_title = self._html_search_regex(
+                r'<h1 class="pl-header-title">\s*(.*?)\s*</h1>', page, u'title')
 
         url_results = self._ids_to_results(ids)
         return self.playlist_result(url_results, playlist_id, playlist_title)

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.02.19'
+__version__ = '2014.02.21'