release 2015.02.26

Some of them may be an 'url' result, which in general don't have the 'title' field.

README.md

@@ -139,6 +139,8 @@ which means you can modify it, redistribute it or use it however you like.
                                      dislike_count <? 50 & description" .
     --no-playlist                    If the URL refers to a video and a
                                      playlist, download only the video.
+    --yes-playlist                   If the URL refers to a video and a
+                                     playlist, download the playlist.
     --age-limit YEARS                download only videos suitable for the given
                                      age
     --download-archive FILE          Download only videos not listed in the

test/test_subtitles.py

@@ -25,6 +25,7 @@ from youtube_dl.extractor import (
     RaiIE,
     VikiIE,
     ThePlatformIE,
+    RTVEALaCartaIE,
 )
 
 
@@ -305,5 +306,19 @@ class TestThePlatformSubtitles(BaseTestSubtitles):
         self.assertEqual(md5(subtitles['en']), '97e7670cbae3c4d26ae8bcc7fdd78d4b')
 
 
+class TestRtveSubtitles(BaseTestSubtitles):
+    url = 'http://www.rtve.es/alacarta/videos/los-misterios-de-laura/misterios-laura-capitulo-32-misterio-del-numero-17-2-parte/2428621/'
+    IE = RTVEALaCartaIE
+
+    def test_allsubtitles(self):
+        print('Skipping, only available from Spain')
+        return
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['es']))
+        self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca')
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -85,6 +85,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(
             sanitize_filename('New World record at 0:12:34'),
             'New World record at 0_12_34')
+        self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
+        self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
 
         forbidden = '"\0\\/'
         for fc in forbidden:

youtube_dl/extractor/bloomberg.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 
 
 class BloombergIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?)\.html'
+    _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<id>.+?)\.html'
 
     _TEST = {
         'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
@@ -20,9 +20,9 @@ class BloombergIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        name = self._match_id(url)
-        name = mobj.group('name')
         webpage = self._download_webpage(url, name)
+
         f4m_url = self._search_regex(
             r'<source src="(https?://[^"]+\.f4m.*?)"', webpage,
             'f4m url')

youtube_dl/extractor/eporner.py

@@ -35,10 +35,7 @@ class EpornerIE(InfoExtractor):
         title = self._html_search_regex(
             r'<title>(.*?) - EPORNER', webpage, 'title')
 
-        redirect_code = self._html_search_regex(
+        redirect_url = 'http://www.eporner.com/config5/%s' % video_id
-            r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id,
-            webpage, 'redirect_code')
-        redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code)
         player_code = self._download_webpage(
             redirect_url, display_id, note='Downloading player config')
 
@@ -69,5 +66,5 @@ class EpornerIE(InfoExtractor):
             'duration': duration,
             'view_count': view_count,
             'formats': formats,
-            'age_limit': self._rta_search(webpage),
+            'age_limit': 18,
         }

youtube_dl/extractor/escapist.py

@@ -42,7 +42,14 @@ class EscapistIE(InfoExtractor):
         title = raw_title.partition(' : ')[2]
 
         config_url = compat_urllib_parse.unquote(self._html_search_regex(
-            r'<param\s+name="flashvars"\s+value="config=([^"&]+)', webpage, 'config URL'))
+            r'''(?x)
+            (?:
+                <param\s+name="flashvars".*?\s+value="config=|
+                flashvars=&quot;config=
+            )
+            (https?://[^"&]+)
+            ''',
+            webpage, 'config URL'))
 
         formats = []
 

youtube_dl/extractor/facebook.py

@@ -126,11 +126,17 @@ class FacebookIE(InfoExtractor):
         params_raw = compat_urllib_parse.unquote(data['params'])
         params = json.loads(params_raw)
         video_data = params['video_data'][0]
-        video_url = video_data.get('hd_src')
+
-        if not video_url:
+        formats = []
-            video_url = video_data['sd_src']
+        for quality in ['sd', 'hd']:
-        if not video_url:
+            src = video_data.get('%s_src' % quality)
-            raise ExtractorError('Cannot find video URL')
+            if src is not None:
+                formats.append({
+                    'format_id': quality,
+                    'url': src,
+                })
+        if not formats:
+            raise ExtractorError('Cannot find video formats')
 
         video_title = self._html_search_regex(
             r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title',
@@ -146,7 +152,7 @@ class FacebookIE(InfoExtractor):
         return {
             'id': video_id,
             'title': video_title,
-            'url': video_url,
+            'formats': formats,
             'duration': int_or_none(video_data.get('video_duration')),
             'thumbnail': video_data.get('thumbnail_src'),
         }

youtube_dl/extractor/generic.py

@@ -1208,6 +1208,8 @@ class GenericIE(InfoExtractor):
             return entries[0]
         else:
             for num, e in enumerate(entries, start=1):
+                # 'url' results don't have a title
+                if e.get('title') is not None:
                     e['title'] = '%s (%d)' % (e['title'], num)
             return {
                 '_type': 'playlist',

youtube_dl/extractor/laola1tv.py

@@ -1,23 +1,26 @@
+# -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
 import random
 import re
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    xpath_text,
+)
 
 
 class Laola1TvIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/.*?/(?P<id>[0-9]+)\.html'
     _TEST = {
-        'url': 'http://www.laola1.tv/de-de/live/bwf-bitburger-open-grand-prix-gold-court-1/250019.html',
+        'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
         'info_dict': {
-            'id': '250019',
+            'id': '227883',
             'ext': 'mp4',
-            'title': 'Bitburger Open Grand Prix Gold - Court 1',
+            'title': 'Straubing Tigers - Kölner Haie',
-            'categories': ['Badminton'],
+            'categories': ['Eishockey'],
-            'uploader': 'BWF - Badminton World Federation',
+            'is_live': False,
-            'is_live': True,
         },
         'params': {
             'skip_download': True,
@@ -43,15 +46,26 @@ class Laola1TvIE(InfoExtractor):
             r'flashvars\.([_a-zA-Z0-9]+)\s*=\s*"([^"]*)";', iframe)
         flashvars = dict((m[0], m[1]) for m in flashvars_m)
 
+        partner_id = self._search_regex(
+            r'partnerid\s*:\s*"([^"]+)"', iframe, 'partner id')
+
         xml_url = ('http://www.laola1.tv/server/hd_video.php?' +
-                   'play=%s&partner=1&portal=%s&v5ident=&lang=%s' % (
+                   'play=%s&partner=%s&portal=%s&v5ident=&lang=%s' % (
-                       video_id, portal, lang))
+                       video_id, partner_id, portal, lang))
         hd_doc = self._download_xml(xml_url, video_id)
 
-        title = hd_doc.find('.//video/title').text
+        title = xpath_text(hd_doc, './/video/title', fatal=True)
-        flash_url = hd_doc.find('.//video/url').text
+        flash_url = xpath_text(hd_doc, './/video/url', fatal=True)
-        categories = hd_doc.find('.//video/meta_sports').text.split(',')
+        uploader = xpath_text(hd_doc, './/video/meta_organistation')
-        uploader = hd_doc.find('.//video/meta_organistation').text
+
+        is_live = xpath_text(hd_doc, './/video/islive') == 'true'
+        if is_live:
+            raise ExtractorError(
+                'Live streams are not supported by the f4m downloader.')
+
+        categories = xpath_text(hd_doc, './/video/meta_sports')
+        if categories:
+            categories = categories.split(',')
 
         ident = random.randint(10000000, 99999999)
         token_url = '%s&ident=%s&klub=0&unikey=0&timestamp=%s&auth=%s' % (
@@ -60,15 +74,16 @@ class Laola1TvIE(InfoExtractor):
         token_doc = self._download_xml(
             token_url, video_id, note='Downloading token')
         token_attrib = token_doc.find('.//token').attrib
-        if token_attrib.get('auth') == 'blocked':
+        if token_attrib.get('auth') in ('blocked', 'restricted'):
-            raise ExtractorError('Token error: ' % token_attrib.get('comment'))
+            raise ExtractorError(
+                'Token error: %s' % token_attrib.get('comment'), expected=True)
 
         video_url = '%s?hdnea=%s&hdcore=3.2.0' % (
             token_attrib['url'], token_attrib['auth'])
 
         return {
             'id': video_id,
-            'is_live': True,
+            'is_live': is_live,
             'title': title,
             'url': video_url,
             'uploader': uploader,

youtube_dl/extractor/mitele.py

@@ -18,7 +18,7 @@ class MiTeleIE(InfoExtractor):
     IE_NAME = 'mitele.es'
     _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
         'md5': '6a75fe9d0d3275bead0cb683c616fddb',
         'info_dict': {
@@ -29,7 +29,7 @@ class MiTeleIE(InfoExtractor):
             'display_id': 'programa-144',
             'duration': 2913,
         },
-    }
+    }]
 
     def _real_extract(self, url):
         episode = self._match_id(url)

youtube_dl/extractor/nrk.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     float_or_none,
@@ -158,7 +159,9 @@ class NRKTVIE(InfoExtractor):
     def _get_subtitles(self, subtitlesurl, video_id, baseurl):
         url = "%s%s" % (baseurl, subtitlesurl)
         self._debug_print('%s: Subtitle url: %s' % (video_id, url))
-        captions = self._download_xml(url, video_id, 'Downloading subtitles')
+        captions = self._download_xml(
+            url, video_id, 'Downloading subtitles',
+            transform_source=lambda s: s.replace(r'<br />', '\r\n'))
         lang = captions.get('lang', 'no')
         ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/ns/ttml}'))
         srt = ''
@@ -167,8 +170,7 @@ class NRKTVIE(InfoExtractor):
             duration = parse_duration(p.get('dur'))
             starttime = self._seconds2str(begin)
             endtime = self._seconds2str(begin + duration)
-            text = '\n'.join(p.itertext())
+            srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (compat_str(pos), starttime, endtime, p.text)
-            srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), starttime, endtime, text)
         return {lang: [
             {'ext': 'ttml', 'url': url},
             {'ext': 'srt', 'data': srt},

youtube_dl/extractor/rtve.py

@@ -102,14 +102,27 @@ class RTVEALaCartaIE(InfoExtractor):
             video_url = compat_urlparse.urljoin(
                 'http://mvod1.akcdn.rtve.es/', video_path)
 
+        subtitles = None
+        if info.get('sbtFile') is not None:
+            subtitles = self.extract_subtitles(video_id, info['sbtFile'])
+
         return {
             'id': video_id,
             'title': info['title'],
             'url': video_url,
             'thumbnail': info.get('image'),
             'page_url': url,
+            'subtitles': subtitles,
         }
 
+    def _get_subtitles(self, video_id, sub_file):
+        subs = self._download_json(
+            sub_file + '.json', video_id,
+            'Downloading subtitles info')['page']['items']
+        return dict(
+            (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
+            for s in subs)
+
 
 class RTVELiveIE(InfoExtractor):
     IE_NAME = 'rtve.es:live'

youtube_dl/extractor/telecinco.py

@@ -6,9 +6,9 @@ from .mitele import MiTeleIE
 
 class TelecincoIE(MiTeleIE):
     IE_NAME = 'telecinco.es'
-    _VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/[^/]+/(?P<id>.*?)\.html'
+    _VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/(?:[^/]+/)?(?P<id>.*?)\.html'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html',
         'info_dict': {
             'id': 'MDSVID20141015_0058',
@@ -16,4 +16,7 @@ class TelecincoIE(MiTeleIE):
             'title': 'Con Martín Berasategui, hacer un bacalao al ...',
             'duration': 662,
         },
-    }
+    }, {
+        'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html',
+        'only_matching': True,
+    }]

youtube_dl/extractor/youtube.py

@@ -1153,13 +1153,13 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
                         |  p/
                         )
                         (
-                            (?:PL|LL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,}
+                            (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,}
                             # Top tracks, they can also include dots
                             |(?:MC)[\w\.]*
                         )
                         .*
                      |
-                        ((?:PL|LL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,})
+                        ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,})
                      )"""
     _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
     _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)'
@@ -1244,7 +1244,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
             for vid_id in ids]
 
     def _extract_mix(self, playlist_id):
-        # The mixes are generated from a a single video
+        # The mixes are generated from a single video
         # the id of the playlist is just 'RD' + video_id
         url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id)
         webpage = self._download_webpage(
@@ -1280,7 +1280,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
             else:
                 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
 
-        if playlist_id.startswith('RD'):
+        if playlist_id.startswith('RD') or playlist_id.startswith('UL'):
             # Mixes require a custom extraction process
             return self._extract_mix(playlist_id)
 

youtube_dl/options.py

@@ -272,6 +272,10 @@ def parseOpts(overrideArguments=None):
         '--no-playlist',
         action='store_true', dest='noplaylist', default=False,
         help='If the URL refers to a video and a playlist, download only the video.')
+    selection.add_option(
+        '--yes-playlist',
+        action='store_false', dest='noplaylist', default=False,
+        help='If the URL refers to a video and a playlist, download the playlist.')
     selection.add_option(
         '--age-limit',
         metavar='YEARS', dest='age_limit', default=None, type=int,

youtube_dl/utils.py

@@ -54,7 +54,7 @@ from .compat import (
 compiled_regex_type = type(re.compile(''))
 
 std_headers = {
-    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0 (Chrome)',
+    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/20.0 (Chrome)',
     'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
     'Accept-Encoding': 'gzip, deflate',
@@ -304,6 +304,8 @@ def sanitize_filename(s, restricted=False, is_id=False):
         # Common case of "Foreign band name - English song title"
         if restricted and result.startswith('-_'):
             result = result[2:]
+        if result.startswith('-'):
+            result = '_' + result[len('-'):]
         if not result:
             result = '_'
     return result

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2015.02.23.1'
+__version__ = '2015.02.26'