aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py3
-rw-r--r--youtube_dl/extractor/chilloutzone.py2
-rw-r--r--youtube_dl/extractor/cnn.py2
-rw-r--r--youtube_dl/extractor/drtv.py37
-rw-r--r--youtube_dl/extractor/mitele.py9
-rw-r--r--youtube_dl/extractor/nba.py20
-rw-r--r--youtube_dl/extractor/nextmedia.py40
-rw-r--r--youtube_dl/extractor/prosiebensat1.py2
-rw-r--r--youtube_dl/extractor/rtve.py2
-rw-r--r--youtube_dl/extractor/rutv.py2
-rw-r--r--youtube_dl/extractor/shared.py2
-rw-r--r--youtube_dl/extractor/sportbox.py26
-rw-r--r--youtube_dl/extractor/telecinco.py4
-rw-r--r--youtube_dl/extractor/tutv.py2
-rw-r--r--youtube_dl/extractor/videott.py2
-rw-r--r--youtube_dl/extractor/viki.py5
16 files changed, 94 insertions, 66 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 24efb7ce5..8bb3926a0 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -338,8 +338,7 @@ from .newstube import NewstubeIE
from .nextmedia import (
NextMediaIE,
NextMediaActionNewsIE,
- AppleDailyRealtimeNewsIE,
- AppleDailyAnimationNewsIE
+ AppleDailyIE,
)
from .nfb import NFBIE
from .nfl import NFLIE
diff --git a/youtube_dl/extractor/chilloutzone.py b/youtube_dl/extractor/chilloutzone.py
index c922f6959..0206d96db 100644
--- a/youtube_dl/extractor/chilloutzone.py
+++ b/youtube_dl/extractor/chilloutzone.py
@@ -57,7 +57,7 @@ class ChilloutzoneIE(InfoExtractor):
base64_video_info = self._html_search_regex(
r'var cozVidData = "(.+?)";', webpage, 'video data')
- decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
+ decoded_video_info = base64.b64decode(base64_video_info.encode('utf-8')).decode('utf-8')
video_info_dict = json.loads(decoded_video_info)
# get video information from dict
diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py
index 5efc5f4fe..3b1bd4033 100644
--- a/youtube_dl/extractor/cnn.py
+++ b/youtube_dl/extractor/cnn.py
@@ -12,7 +12,7 @@ from ..utils import (
class CNNIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/
- (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z]{3,5})(?:-ap)?|(?=&)))'''
+ (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z\-]+)|(?=&)))'''
_TESTS = [{
'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py
index f25ab319e..baa24c6d1 100644
--- a/youtube_dl/extractor/drtv.py
+++ b/youtube_dl/extractor/drtv.py
@@ -1,8 +1,11 @@
# coding: utf-8
from __future__ import unicode_literals
-from .common import InfoExtractor, ExtractorError
-from ..utils import parse_iso8601
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+ parse_iso8601,
+)
class DRTVIE(InfoExtractor):
@@ -60,19 +63,31 @@ class DRTVIE(InfoExtractor):
restricted_to_denmark = asset['RestrictedToDenmark']
spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
for link in asset['Links']:
- target = link['Target']
uri = link['Uri']
+ target = link['Target']
format_id = target
- preference = -1 if target == 'HDS' else -2
+ preference = None
if spoken_subtitles:
- preference -= 2
+ preference = -1
format_id += '-spoken-subtitles'
- formats.append({
- 'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri,
- 'format_id': format_id,
- 'ext': link['FileFormat'],
- 'preference': preference,
- })
+ if target == 'HDS':
+ formats.extend(self._extract_f4m_formats(
+ uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
+ video_id, preference, f4m_id=format_id))
+ elif target == 'HLS':
+ formats.extend(self._extract_m3u8_formats(
+ uri, video_id, 'mp4', preference=preference,
+ m3u8_id=format_id))
+ else:
+ bitrate = link.get('Bitrate')
+ if bitrate:
+ format_id += '-%s' % bitrate
+ formats.append({
+ 'url': uri,
+ 'format_id': format_id,
+ 'tbr': bitrate,
+ 'ext': link.get('FileFormat'),
+ })
subtitles_list = asset.get('SubtitlesList')
if isinstance(subtitles_list, list):
LANGS = {
diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py
index d8897eb90..7091f3335 100644
--- a/youtube_dl/extractor/mitele.py
+++ b/youtube_dl/extractor/mitele.py
@@ -20,7 +20,6 @@ class MiTeleIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
- 'md5': '6a75fe9d0d3275bead0cb683c616fddb',
'info_dict': {
'id': '0fce117d',
'ext': 'mp4',
@@ -29,6 +28,10 @@ class MiTeleIE(InfoExtractor):
'display_id': 'programa-144',
'duration': 2913,
},
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
}]
def _real_extract(self, url):
@@ -56,12 +59,14 @@ class MiTeleIE(InfoExtractor):
episode,
transform_source=strip_jsonp
)
+ formats = self._extract_m3u8_formats(
+ token_info['tokenizedUrl'], episode, ext='mp4')
return {
'id': embed_data['videoId'],
'display_id': episode,
'title': info_el.find('title').text,
- 'url': token_info['tokenizedUrl'],
+ 'formats': formats,
'description': get_element_by_attribute('class', 'text', webpage),
'thumbnail': info_el.find('thumb').text,
'duration': parse_duration(info_el.find('duration').text),
diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py
index 862b706bf..944096e1c 100644
--- a/youtube_dl/extractor/nba.py
+++ b/youtube_dl/extractor/nba.py
@@ -22,6 +22,18 @@ class NBAIE(InfoExtractor):
}, {
'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/',
'only_matching': True,
+ }, {
+ 'url': 'http://watch.nba.com/nba/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
+ 'info_dict': {
+ 'id': '0041400301-cle-atl-recap.nba',
+ 'ext': 'mp4',
+ 'title': 'NBA GAME TIME | Video: Hawks vs. Cavaliers Game 1',
+ 'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d',
+ 'duration': 228,
+ },
+ 'params': {
+ 'skip_download': True,
+ }
}]
def _real_extract(self, url):
@@ -35,8 +47,12 @@ class NBAIE(InfoExtractor):
self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com')
description = self._og_search_description(webpage)
- duration = parse_duration(
- self._html_search_meta('duration', webpage, 'duration'))
+ duration_str = self._html_search_meta(
+ 'duration', webpage, 'duration', default=None)
+ if not duration_str:
+ duration_str = self._html_search_regex(
+ r'Duration:</b>\s*(\d+:\d+)', webpage, 'duration', fatal=False)
+ duration = parse_duration(duration_str)
return {
'id': shortened_video_id,
diff --git a/youtube_dl/extractor/nextmedia.py b/youtube_dl/extractor/nextmedia.py
index 02dba4ef6..d1b7cff4c 100644
--- a/youtube_dl/extractor/nextmedia.py
+++ b/youtube_dl/extractor/nextmedia.py
@@ -89,8 +89,8 @@ class NextMediaActionNewsIE(NextMediaIE):
return self._extract_from_nextmedia_page(news_id, url, article_page)
-class AppleDailyRealtimeNewsIE(NextMediaIE):
- _VALID_URL = r'http://(www|ent).appledaily.com.tw/(realtimenews|enews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
+class AppleDailyIE(NextMediaIE):
+ _VALID_URL = r'http://(www|ent).appledaily.com.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
_TESTS = [{
'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
@@ -99,7 +99,7 @@ class AppleDailyRealtimeNewsIE(NextMediaIE):
'ext': 'mp4',
'title': '周亭羽走過摩鐵陰霾2男陪吃 九把刀孤寒看醫生',
'thumbnail': 're:^https?://.*\.jpg$',
- 'description': 'md5:b23787119933404ce515c6356a8c355c',
+ 'description': 'md5:2acd430e59956dc47cd7f67cb3c003f4',
'upload_date': '20150128',
}
}, {
@@ -110,26 +110,10 @@ class AppleDailyRealtimeNewsIE(NextMediaIE):
'ext': 'mp4',
'title': '不滿被踩腳　山東兩大媽一路打下車',
'thumbnail': 're:^https?://.*\.jpg$',
- 'description': 'md5:2648aaf6fc4f401f6de35a91d111aa1d',
+ 'description': 'md5:175b4260c1d7c085993474217e4ab1b4',
'upload_date': '20150128',
}
- }]
-
- _URL_PATTERN = r'\{url: \'(.+)\'\}'
-
- def _fetch_title(self, page):
- return self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title')
-
- def _fetch_thumbnail(self, page):
- return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False)
-
- def _fetch_timestamp(self, page):
- return None
-
-
-class AppleDailyAnimationNewsIE(AppleDailyRealtimeNewsIE):
- _VALID_URL = 'http://www.appledaily.com.tw/animation/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
- _TESTS = [{
+ }, {
'url': 'http://www.appledaily.com.tw/animation/realtimenews/new/20150128/5003671',
'md5': '03df296d95dedc2d5886debbb80cb43f',
'info_dict': {
@@ -154,10 +138,22 @@ class AppleDailyAnimationNewsIE(AppleDailyRealtimeNewsIE):
'expected_warnings': [
'video thumbnail',
]
+ }, {
+ 'url': 'http://www.appledaily.com.tw/appledaily/article/supplement/20140417/35770334/',
+ 'only_matching': True,
}]
+ _URL_PATTERN = r'\{url: \'(.+)\'\}'
+
def _fetch_title(self, page):
- return self._html_search_meta('description', page, 'news title')
+ return (self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title', default=None) or
+ self._html_search_meta('description', page, 'news title'))
+
+ def _fetch_thumbnail(self, page):
+ return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False)
+
+ def _fetch_timestamp(self, page):
+ return None
def _fetch_description(self, page):
return self._html_search_meta('description', page, 'news description')
diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py
index 7cc799664..255d4abc1 100644
--- a/youtube_dl/extractor/prosiebensat1.py
+++ b/youtube_dl/extractor/prosiebensat1.py
@@ -17,7 +17,7 @@ from ..utils import (
class ProSiebenSat1IE(InfoExtractor):
IE_NAME = 'prosiebensat1'
IE_DESC = 'ProSiebenSat.1 Digital'
- _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|ran|the-voice-of-germany)\.de|fem\.com)/(?P<id>.+)'
+ _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at)|ran\.de|fem\.com)/(?P<id>.+)'
_TESTS = [
{
diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py
index 849300140..82cd98ac7 100644
--- a/youtube_dl/extractor/rtve.py
+++ b/youtube_dl/extractor/rtve.py
@@ -17,7 +17,7 @@ from ..utils import (
def _decrypt_url(png):
- encrypted_data = base64.b64decode(png)
+ encrypted_data = base64.b64decode(png.encode('utf-8'))
text_index = encrypted_data.find(b'tEXt')
text_chunk = encrypted_data[text_index - 4:]
length = struct_unpack('!I', text_chunk[:4])[0]
diff --git a/youtube_dl/extractor/rutv.py b/youtube_dl/extractor/rutv.py
index 55604637d..d9df06861 100644
--- a/youtube_dl/extractor/rutv.py
+++ b/youtube_dl/extractor/rutv.py
@@ -104,7 +104,7 @@ class RUTVIE(InfoExtractor):
@classmethod
def _extract_url(cls, webpage):
mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.rutv\.ru/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage)
+ r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage)
if mobj:
return mobj.group('url')
diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py
index 26ced716e..9f3e944e7 100644
--- a/youtube_dl/extractor/shared.py
+++ b/youtube_dl/extractor/shared.py
@@ -47,7 +47,7 @@ class SharedIE(InfoExtractor):
video_url = self._html_search_regex(
r'data-url="([^"]+)"', video_page, 'video URL')
title = base64.b64decode(self._html_search_meta(
- 'full:title', webpage, 'title')).decode('utf-8')
+ 'full:title', webpage, 'title').encode('utf-8')).decode('utf-8')
filesize = int_or_none(self._html_search_meta(
'full:size', webpage, 'file size', fatal=False))
thumbnail = self._html_search_regex(
diff --git a/youtube_dl/extractor/sportbox.py b/youtube_dl/extractor/sportbox.py
index 8686f9d11..86d509ae5 100644
--- a/youtube_dl/extractor/sportbox.py
+++ b/youtube_dl/extractor/sportbox.py
@@ -6,8 +6,7 @@ import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
- parse_duration,
- parse_iso8601,
+ unified_strdate,
)
@@ -20,11 +19,9 @@ class SportBoxIE(InfoExtractor):
'id': '80822',
'ext': 'mp4',
'title': 'Гонка 2 заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн',
- 'description': 'md5:81715fa9c4ea3d9e7915dc8180c778ed',
+ 'description': 'md5:3d72dc4a006ab6805d82f037fdc637ad',
'thumbnail': 're:^https?://.*\.jpg$',
- 'timestamp': 1411896237,
'upload_date': '20140928',
- 'duration': 4846,
},
'params': {
# m3u8 download
@@ -48,17 +45,13 @@ class SportBoxIE(InfoExtractor):
r'src="/?(vdl/player/[^"]+)"', webpage, 'player')
title = self._html_search_regex(
- r'<h1 itemprop="name">([^<]+)</h1>', webpage, 'title')
- description = self._html_search_regex(
- r'(?s)<div itemprop="description">(.+?)</div>',
- webpage, 'description', fatal=False)
+ [r'"nodetitle"\s*:\s*"([^"]+)"', r'class="node-header_{1,2}title">([^<]+)'],
+ webpage, 'title')
+ description = self._og_search_description(webpage) or self._html_search_meta(
+ 'description', webpage, 'description')
thumbnail = self._og_search_thumbnail(webpage)
- timestamp = parse_iso8601(self._search_regex(
- r'<span itemprop="uploadDate">([^<]+)</span>',
- webpage, 'timestamp', fatal=False))
- duration = parse_duration(self._html_search_regex(
- r'<meta itemprop="duration" content="PT([^"]+)">',
- webpage, 'duration', fatal=False))
+ upload_date = unified_strdate(self._html_search_meta(
+ 'dateCreated', webpage, 'upload date'))
return {
'_type': 'url_transparent',
@@ -67,8 +60,7 @@ class SportBoxIE(InfoExtractor):
'title': title,
'description': description,
'thumbnail': thumbnail,
- 'timestamp': timestamp,
- 'duration': duration,
+ 'upload_date': upload_date,
}
diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py
index 251a68680..a0c744fd1 100644
--- a/youtube_dl/extractor/telecinco.py
+++ b/youtube_dl/extractor/telecinco.py
@@ -16,6 +16,10 @@ class TelecincoIE(MiTeleIE):
'title': 'Con Martín Berasategui, hacer un bacalao al ...',
'duration': 662,
},
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
}, {
'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html',
'only_matching': True,
diff --git a/youtube_dl/extractor/tutv.py b/youtube_dl/extractor/tutv.py
index 4de0aac52..fad720b68 100644
--- a/youtube_dl/extractor/tutv.py
+++ b/youtube_dl/extractor/tutv.py
@@ -26,7 +26,7 @@ class TutvIE(InfoExtractor):
data_content = self._download_webpage(
'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info')
- video_url = base64.b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8')
+ video_url = base64.b64decode(compat_parse_qs(data_content)['kpt'][0].encode('utf-8')).decode('utf-8')
return {
'id': internal_id,
diff --git a/youtube_dl/extractor/videott.py b/youtube_dl/extractor/videott.py
index ececc7ee0..591024ead 100644
--- a/youtube_dl/extractor/videott.py
+++ b/youtube_dl/extractor/videott.py
@@ -43,7 +43,7 @@ class VideoTtIE(InfoExtractor):
formats = [
{
- 'url': base64.b64decode(res['u']).decode('utf-8'),
+ 'url': base64.b64decode(res['u'].encode('utf-8')).decode('utf-8'),
'ext': 'flv',
'format_id': res['l'],
} for res in settings['res'] if res['u']
diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py
index fe7229952..7f2fb1ca8 100644
--- a/youtube_dl/extractor/viki.py
+++ b/youtube_dl/extractor/viki.py
@@ -15,6 +15,7 @@ from .common import InfoExtractor
class VikiBaseIE(InfoExtractor):
+ _VALID_URL_BASE = r'https?://(?:www\.)?viki\.(?:com|net|mx|jp|fr)/'
_API_QUERY_TEMPLATE = '/v4/%sapp=%s&t=%s&site=www.viki.com'
_API_URL_TEMPLATE = 'http://api.viki.io%s&sig=%s'
@@ -58,7 +59,7 @@ class VikiBaseIE(InfoExtractor):
class VikiIE(VikiBaseIE):
IE_NAME = 'viki'
- _VALID_URL = r'https?://(?:www\.)?viki\.com/(?:videos|player)/(?P<id>[0-9]+v)'
+ _VALID_URL = r'%s(?:videos|player)/(?P<id>[0-9]+v)' % VikiBaseIE._VALID_URL_BASE
_TESTS = [{
'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14',
'info_dict': {
@@ -229,7 +230,7 @@ class VikiIE(VikiBaseIE):
class VikiChannelIE(VikiBaseIE):
IE_NAME = 'viki:channel'
- _VALID_URL = r'https?://(?:www\.)?viki\.com/(?:tv|news|movies|artists)/(?P<id>[0-9]+c)'
+ _VALID_URL = r'%s(?:tv|news|movies|artists)/(?P<id>[0-9]+c)' % VikiBaseIE._VALID_URL_BASE
_TESTS = [{
'url': 'http://www.viki.com/tv/50c-boys-over-flowers',
'info_dict': {
generated by cgit v1.2.3 (git 2.26.2) at 2024-12-21 05:55:59 +0000