aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/bbc.py85
-rw-r--r--youtube_dl/extractor/comcarcoff.py2
-rw-r--r--youtube_dl/extractor/common.py11
-rw-r--r--youtube_dl/extractor/generic.py8
-rw-r--r--youtube_dl/extractor/spiegel.py5
-rw-r--r--youtube_dl/extractor/youtube.py35
6 files changed, 104 insertions, 42 deletions
diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py
index 2a0901ee4..9a1b6e3dc 100644
--- a/youtube_dl/extractor/bbc.py
+++ b/youtube_dl/extractor/bbc.py
@@ -20,7 +20,9 @@ class BBCCoUkIE(InfoExtractor):
IE_DESC = 'BBC iPlayer'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
- _MEDIASELECTOR_URL = 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s'
+ _MEDIASELECTOR_URLS = [
+ 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s',
+ ]
_TESTS = [
{
@@ -162,6 +164,10 @@ class BBCCoUkIE(InfoExtractor):
}
]
+ class MediaSelectionError(Exception):
+ def __init__(self, id):
+ self.id = id
+
def _extract_asx_playlist(self, connection, programme_id):
asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
return [ref.get('href') for ref in asx.findall('./Entry/ref')]
@@ -172,6 +178,7 @@ class BBCCoUkIE(InfoExtractor):
supplier = connection.get('supplier')
if protocol == 'http':
href = connection.get('href')
+ transfer_format = connection.get('transferFormat')
# ASX playlist
if supplier == 'asx':
for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
@@ -179,6 +186,9 @@ class BBCCoUkIE(InfoExtractor):
'url': ref,
'format_id': 'ref%s_%s' % (i, supplier),
})
+ # Skip DASH until supported
+ elif transfer_format == 'dash':
+ pass
# Direct link
else:
formats.append({
@@ -208,8 +218,7 @@ class BBCCoUkIE(InfoExtractor):
def _extract_medias(self, media_selection):
error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error')
if error is not None:
- raise ExtractorError(
- '%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True)
+ raise BBCCoUkIE.MediaSelectionError(error.get('id'))
return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
def _extract_connections(self, media):
@@ -266,9 +275,23 @@ class BBCCoUkIE(InfoExtractor):
]
return subtitles
+ def _raise_extractor_error(self, media_selection_error):
+ raise ExtractorError(
+ '%s returned error: %s' % (self.IE_NAME, media_selection_error.id),
+ expected=True)
+
def _download_media_selector(self, programme_id):
- return self._download_media_selector_url(
- self._MEDIASELECTOR_URL % programme_id, programme_id)
+ last_exception = None
+ for mediaselector_url in self._MEDIASELECTOR_URLS:
+ try:
+ return self._download_media_selector_url(
+ mediaselector_url % programme_id, programme_id)
+ except BBCCoUkIE.MediaSelectionError as e:
+ if e.id == 'notukerror':
+ last_exception = e
+ continue
+ self._raise_extractor_error(e)
+ self._raise_extractor_error(last_exception)
def _download_media_selector_url(self, url, programme_id=None):
try:
@@ -293,7 +316,6 @@ class BBCCoUkIE(InfoExtractor):
formats.extend(self._extract_video(media, programme_id))
elif kind == 'captions':
subtitles = self.extract_subtitles(media, programme_id)
-
return formats, subtitles
def _download_playlist(self, playlist_id):
@@ -422,9 +444,14 @@ class BBCIE(BBCCoUkIE):
IE_DESC = 'BBC'
_VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)'
- # fails with notukerror for some videos
- #_MEDIASELECTOR_URL = 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s'
- _MEDIASELECTOR_URL = 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s'
+ _MEDIASELECTOR_URLS = [
+ # Provides more formats, namely direct mp4 links, but fails on some videos with
+ # notukerror for non UK (?) users (e.g.
+ # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
+ 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s',
+ # Provides fewer formats, but works everywhere for everybody (hopefully)
+ 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s',
+ ]
_TESTS = [{
# article with multiple videos embedded with data-media-meta containing
@@ -447,11 +474,19 @@ class BBCIE(BBCCoUkIE):
'playlist_count': 9,
'skip': 'Save time',
}, {
+ # article with multiple videos embedded with `new SMP()`
+ 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
+ 'info_dict': {
+ 'id': '3662a707-0af9-3149-963f-47bea720b460',
+ 'title': 'BBC Blogs - Adam Curtis - BUGGER',
+ },
+ 'playlist_count': 18,
+ }, {
# single video embedded with mediaAssetPage.init()
'url': 'http://www.bbc.com/news/world-europe-32041533',
'info_dict': {
'id': 'p02mprgb',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
'duration': 47,
'timestamp': 1427219242,
@@ -511,7 +546,7 @@ class BBCIE(BBCCoUkIE):
'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star',
'info_dict': {
'id': 'p018zqqg',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Hyundai Santa Fe Sport: Rock star',
'description': 'md5:b042a26142c4154a6e472933cf20793d',
'timestamp': 1368473503,
@@ -526,7 +561,7 @@ class BBCIE(BBCCoUkIE):
'url': 'http://www.bbc.com/sport/0/football/33653409',
'info_dict': {
'id': 'p02xycnp',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
'description': 'md5:398fca0e2e701c609d726e034fa1fc89',
'duration': 140,
@@ -633,12 +668,30 @@ class BBCIE(BBCCoUkIE):
playlist_title = self._html_search_regex(
r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title')
- playlist_description = self._og_search_description(webpage)
+ playlist_description = self._og_search_description(webpage, default=None)
+
+ def extract_all(pattern):
+ return list(filter(None, map(
+ lambda s: self._parse_json(s, playlist_id, fatal=False),
+ re.findall(pattern, webpage))))
+
+ # Multiple video article (e.g.
+ # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
+ EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?'
+ entries = []
+ for match in extract_all(r'new\s+SMP\(({.+?})\)'):
+ embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
+ if embed_url and re.match(EMBED_URL, embed_url):
+ entries.append(embed_url)
+ entries.extend(re.findall(
+ r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
+ if entries:
+ return self.playlist_result(
+ [self.url_result(entry, 'BBCCoUk') for entry in entries],
+ playlist_id, playlist_title, playlist_description)
# Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
- medias = list(filter(None, map(
- lambda s: self._parse_json(s, playlist_id, fatal=False),
- re.findall(r"data-media-meta='({[^']+})'", webpage))))
+ medias = extract_all(r"data-media-meta='({[^']+})'")
if not medias:
# Single video article (e.g. http://www.bbc.com/news/video_and_audio/international)
diff --git a/youtube_dl/extractor/comcarcoff.py b/youtube_dl/extractor/comcarcoff.py
index 9c25b2223..81f3d7697 100644
--- a/youtube_dl/extractor/comcarcoff.py
+++ b/youtube_dl/extractor/comcarcoff.py
@@ -36,7 +36,7 @@ class ComCarCoffIE(InfoExtractor):
webpage, 'full data json'))
video_id = full_data['activeVideo']['video']
- video_data = full_data['videos'][video_id]
+ video_data = full_data.get('videos', {}).get(video_id) or full_data['singleshots'][video_id]
thumbnails = [{
'url': video_data['images']['thumb'],
}, {
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 14b9b4fe2..d54866d1f 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -181,6 +181,7 @@ class InfoExtractor(object):
by YoutubeDL if it's missing)
categories: A list of categories that the video falls in, for example
["Sports", "Berlin"]
+ tags: A list of tags assigned to the video, e.g. ["sweden", "pop music"]
is_live: True, False, or None (=unknown). Whether this video is a
live stream that goes on instead of a fixed-length video.
start_time: Time in seconds where the reproduction should start, as
@@ -630,6 +631,12 @@ class InfoExtractor(object):
template % (content_re, property_re),
]
+ @staticmethod
+ def _meta_regex(prop):
+ return r'''(?isx)<meta
+ (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
+ [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(prop)
+
def _og_search_property(self, prop, html, name=None, **kargs):
if name is None:
name = 'OpenGraph %s' % prop
@@ -660,9 +667,7 @@ class InfoExtractor(object):
if display_name is None:
display_name = name
return self._html_search_regex(
- r'''(?isx)<meta
- (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
- [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name),
+ self._meta_regex(name),
html, display_name, fatal=fatal, group='content', **kwargs)
def _dc_search_uploader(self, html):
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 6d2efb22e..8cef61c3c 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -276,14 +276,6 @@ class GenericIE(InfoExtractor):
'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
},
},
- # BBC iPlayer embeds
- {
- 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
- 'info_dict': {
- 'title': 'BBC - Blogs - Adam Curtis - BUGGER',
- },
- 'playlist_mincount': 18,
- },
# RUTV embed
{
'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py
index b868241d5..5bd3c0087 100644
--- a/youtube_dl/extractor/spiegel.py
+++ b/youtube_dl/extractor/spiegel.py
@@ -9,7 +9,7 @@ from .spiegeltv import SpiegeltvIE
class SpiegelIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed)?(?:\.html)?(?:#.*)?$'
+ _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$'
_TESTS = [{
'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
'md5': '2c2754212136f35fb4b19767d242f66e',
@@ -39,6 +39,9 @@ class SpiegelIE(InfoExtractor):
'description': 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.',
'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"',
}
+ }, {
+ 'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html',
+ 'only_matching': True,
}]
def _real_extract(self, url):
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 8a5ef2e70..67a1df9a0 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -283,13 +283,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
# Dash webm
- '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
- '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
- '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
- '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
- '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
- '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
- '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'container': 'webm', 'vcodec': 'VP9'},
+ '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
+ '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
+ '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
+ '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
+ '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
+ '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
+ '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'container': 'webm', 'vcodec': 'vp9'},
'242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
@@ -299,11 +299,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
- '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
- '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
- '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
- '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'VP9'},
- '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
+ '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
+ '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
+ '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
+ '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'vp9'},
+ '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
# Dash webm audio
'171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
@@ -331,6 +331,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'upload_date': '20121002',
'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
'categories': ['Science & Technology'],
+ 'tags': ['youtube-dl'],
'like_count': int,
'dislike_count': int,
'start_time': 1,
@@ -345,7 +346,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'ext': 'mp4',
'upload_date': '20120506',
'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
- 'description': 'md5:fea86fda2d5a5784273df5c7cc994d9f',
+ 'description': 'md5:782e8651347686cba06e58f71ab51773',
+ 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
+ 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
+ 'iconic ep', 'iconic', 'love', 'it'],
'uploader': 'Icona Pop',
'uploader_id': 'IconaPop',
}
@@ -1171,6 +1175,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
else:
video_categories = None
+ video_tags = [
+ unescapeHTML(m.group('content'))
+ for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
+
def _extract_count(count_name):
return str_to_int(self._search_regex(
r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
@@ -1339,6 +1347,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'thumbnail': video_thumbnail,
'description': video_description,
'categories': video_categories,
+ 'tags': video_tags,
'subtitles': video_subtitles,
'automatic_captions': automatic_captions,
'duration': video_duration,