commit 2c28da8e05f018d021d52dd1e8bc44bfbb6dbf00
parent 7ba71e30fb9ec188d122f79a914f688928e80e91
Author: remitamine <remitamine@gmail.com>
Date: Mon, 21 Dec 2015 11:18:32 +0100
Merge branch 'bleacherreport' of github.com:remitamine/youtube-dl into remitamine-bleacherreport
Diffstat:
5 files changed, 218 insertions(+), 118 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -61,6 +61,10 @@ from .beatportpro import BeatportProIE
from .bet import BetIE
from .bild import BildIE
from .bilibili import BiliBiliIE
+from .bleacherreport import (
+ BleacherReportIE,
+ BleacherReportCMSIE,
+)
from .blinkx import BlinkxIE
from .bloomberg import BloombergIE
from .bpb import BpbIE
diff --git a/youtube_dl/extractor/amp.py b/youtube_dl/extractor/amp.py
@@ -0,0 +1,84 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+ parse_iso8601,
+)
+
+
+class AMPIE(InfoExtractor):
+ # parse Akamai Adaptive Media Player feed
+ def _extract_feed_info(self, url):
+ item = self._download_json(
+ url, None, 'Downloading Akamai AMP feed',
+ 'Unable to download Akamai AMP feed')['channel']['item']
+
+ video_id = item['guid']
+
+ def get_media_node(name, default=None):
+ media_name = 'media-%s' % name
+ media_group = item.get('media-group') or item
+ return media_group.get(media_name) or item.get(media_name) or item.get(name, default)
+
+ thumbnails = []
+ media_thumbnail = get_media_node('thumbnail')
+ if media_thumbnail:
+ if isinstance(media_thumbnail, dict):
+ media_thumbnail = [media_thumbnail]
+ for thumbnail_data in media_thumbnail:
+ thumbnail = thumbnail_data['@attributes']
+ thumbnails.append({
+ 'url': self._proto_relative_url(thumbnail['url'], 'http:'),
+ 'width': int_or_none(thumbnail.get('width')),
+ 'height': int_or_none(thumbnail.get('height')),
+ })
+
+ subtitles = {}
+ media_subtitle = get_media_node('subTitle')
+ if media_subtitle:
+ if isinstance(media_subtitle, dict):
+ media_subtitle = [media_subtitle]
+ for subtitle_data in media_subtitle:
+ subtitle = subtitle_data['@attributes']
+ lang = subtitle.get('lang') or 'en'
+ subtitles[lang] = [{'url': subtitle['href']}]
+
+ formats = []
+ media_content = get_media_node('content')
+ if isinstance(media_content, dict):
+ media_content = [media_content]
+ for media_data in media_content:
+ media = media_data['@attributes']
+ media_type = media['type']
+ if media_type == 'video/f4m':
+ f4m_formats = self._extract_f4m_formats(
+ media['url'] + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124',
+ video_id, f4m_id='hds', fatal=False)
+ if f4m_formats:
+ formats.extend(f4m_formats)
+ elif media_type == 'application/x-mpegURL':
+ m3u8_formats = self._extract_m3u8_formats(
+ media['url'], video_id, 'mp4', m3u8_id='hls', fatal=False)
+ if m3u8_formats:
+ formats.extend(m3u8_formats)
+ else:
+ formats.append({
+ 'format_id': media_data['media-category']['@attributes']['label'],
+ 'url': media['url'],
+ 'tbr': int_or_none(media.get('bitrate')),
+ 'filesize': int_or_none(media.get('fileSize')),
+ })
+
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': get_media_node('title'),
+ 'description': get_media_node('description'),
+ 'thumbnails': thumbnails,
+ 'timestamp': parse_iso8601(item.get('pubDate'), ' '),
+ 'duration': int_or_none(media_content[0].get('@attributes', {}).get('duration')),
+ 'formats': formats,
+ }
diff --git a/youtube_dl/extractor/bleacherreport.py b/youtube_dl/extractor/bleacherreport.py
@@ -0,0 +1,106 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .amp import AMPIE
+from ..utils import (
+ ExtractorError,
+ int_or_none,
+ parse_iso8601,
+)
+
+
+class BleacherReportIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/articles/(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'http://bleacherreport.com/articles/2496438-fsu-stat-projections-is-jalen-ramsey-best-defensive-player-in-college-football',
+ 'md5': 'a3ffc3dc73afdbc2010f02d98f990f20',
+ 'info_dict': {
+ 'id': '2496438',
+ 'ext': 'mp4',
+ 'title': 'FSU Stat Projections: Is Jalen Ramsey Best Defensive Player in College Football?',
+ 'uploader_id': 3992341,
+ 'description': 'CFB, ACC, Florida State',
+ 'timestamp': 1434380212,
+ 'upload_date': '20150615',
+ 'uploader': 'Team Stream Now ',
+ },
+ 'add_ie': ['Ooyala'],
+ }, {
+ 'url': 'http://bleacherreport.com/articles/2586817-aussie-golfers-get-fright-of-their-lives-after-being-chased-by-angry-kangaroo',
+ 'md5': 'af5f90dc9c7ba1c19d0a3eac806bbf50',
+ 'info_dict': {
+ 'id': '2586817',
+ 'ext': 'mp4',
+ 'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo',
+ 'timestamp': 1446839961,
+ 'uploader': 'Sean Fay',
+ 'description': 'md5:825e94e0f3521df52fa83b2ed198fa20',
+ 'uploader_id': 6466954,
+ 'upload_date': '20151011',
+ },
+ 'add_ie': ['Youtube'],
+ }]
+
+ def _real_extract(self, url):
+ article_id = self._match_id(url)
+
+ article_data = self._download_json('http://api.bleacherreport.com/api/v1/articles/%s' % article_id, article_id)['article']
+
+ thumbnails = []
+ primary_photo = article_data.get('primaryPhoto')
+ if primary_photo:
+ thumbnails = [{
+ 'url': primary_photo['url'],
+ 'width': primary_photo.get('width'),
+ 'height': primary_photo.get('height'),
+ }]
+
+ info = {
+ '_type': 'url_transparent',
+ 'id': article_id,
+ 'title': article_data['title'],
+ 'uploader': article_data.get('author', {}).get('name'),
+ 'uploader_id': article_data.get('authorId'),
+ 'timestamp': parse_iso8601(article_data.get('createdAt')),
+ 'thumbnails': thumbnails,
+ 'comment_count': int_or_none(article_data.get('commentsCount')),
+ 'view_count': int_or_none(article_data.get('hitCount')),
+ }
+
+ video = article_data.get('video')
+ if video:
+ video_type = video['type']
+ if video_type == 'cms.bleacherreport.com':
+ info['url'] = 'http://bleacherreport.com/video_embed?id=%s' % video['id']
+ elif video_type == 'ooyala.com':
+ info['url'] = 'ooyala:%s' % video['id']
+ elif video_type == 'youtube.com':
+ info['url'] = video['id']
+ elif video_type == 'vine.co':
+ info['url'] = 'https://vine.co/v/%s' % video['id']
+ else:
+ info['url'] = video_type + video['id']
+ return info
+ else:
+ raise ExtractorError('no video in the article', expected=True)
+
+
+class BleacherReportCMSIE(AMPIE):
+ _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36})'
+ _TESTS = [{
+ 'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
+ 'md5': 'f0ca220af012d4df857b54f792c586bb',
+ 'info_dict': {
+ 'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
+ 'ext': 'flv',
+ 'title': 'Cena vs. Rollins Would Expose the Heavyweight Division',
+ 'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e',
+ },
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ info = self._extract_feed_info('http://cms.bleacherreport.com/media/items/%s/akamai.json' % video_id)
+ info['id'] = video_id
+ return info
diff --git a/youtube_dl/extractor/dramafever.py b/youtube_dl/extractor/dramafever.py
@@ -3,7 +3,7 @@ from __future__ import unicode_literals
import itertools
-from .common import InfoExtractor
+from .amp import AMPIE
from ..compat import (
compat_HTTPError,
compat_urllib_parse,
@@ -12,14 +12,11 @@ from ..compat import (
from ..utils import (
ExtractorError,
clean_html,
- determine_ext,
- int_or_none,
- parse_iso8601,
sanitized_Request,
)
-class DramaFeverBaseIE(InfoExtractor):
+class DramaFeverBaseIE(AMPIE):
_LOGIN_URL = 'https://www.dramafever.com/accounts/login/'
_NETRC_MACHINE = 'dramafever'
@@ -80,60 +77,25 @@ class DramaFeverIE(DramaFeverBaseIE):
'timestamp': 1404336058,
'upload_date': '20140702',
'duration': 343,
- }
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
}
def _real_extract(self, url):
video_id = self._match_id(url).replace('/', '.')
try:
- feed = self._download_json(
- 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id,
- video_id, 'Downloading episode JSON')['channel']['item']
+ info = self._extract_feed_info(
+ 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
raise ExtractorError(
'Currently unavailable in your country.', expected=True)
raise
- media_group = feed.get('media-group', {})
-
- formats = []
- for media_content in media_group['media-content']:
- src = media_content.get('@attributes', {}).get('url')
- if not src:
- continue
- ext = determine_ext(src)
- if ext == 'f4m':
- formats.extend(self._extract_f4m_formats(
- src, video_id, f4m_id='hds'))
- elif ext == 'm3u8':
- formats.extend(self._extract_m3u8_formats(
- src, video_id, 'mp4', m3u8_id='hls'))
- else:
- formats.append({
- 'url': src,
- })
- self._sort_formats(formats)
-
- title = media_group.get('media-title')
- description = media_group.get('media-description')
- duration = int_or_none(media_group['media-content'][0].get('@attributes', {}).get('duration'))
- thumbnail = self._proto_relative_url(
- media_group.get('media-thumbnail', {}).get('@attributes', {}).get('url'))
- timestamp = parse_iso8601(feed.get('pubDate'), ' ')
-
- subtitles = {}
- for media_subtitle in media_group.get('media-subTitle', []):
- lang = media_subtitle.get('@attributes', {}).get('lang')
- href = media_subtitle.get('@attributes', {}).get('href')
- if not lang or not href:
- continue
- subtitles[lang] = [{
- 'ext': 'ttml',
- 'url': href,
- }]
-
series_id, episode_number = video_id.split('.')
episode_info = self._download_json(
# We only need a single episode info, so restricting page size to one episode
@@ -146,21 +108,12 @@ class DramaFeverIE(DramaFeverBaseIE):
if value:
subfile = value[0].get('subfile') or value[0].get('new_subfile')
if subfile and subfile != 'http://www.dramafever.com/st/':
- subtitles.setdefault('English', []).append({
+ info['subtitiles'].setdefault('English', []).append({
'ext': 'srt',
'url': subfile,
})
- return {
- 'id': video_id,
- 'title': title,
- 'description': description,
- 'thumbnail': thumbnail,
- 'timestamp': timestamp,
- 'duration': duration,
- 'formats': formats,
- 'subtitles': subtitles,
- }
+ return info
class DramaFeverSeriesIE(DramaFeverBaseIE):
diff --git a/youtube_dl/extractor/foxnews.py b/youtube_dl/extractor/foxnews.py
@@ -2,14 +2,10 @@ from __future__ import unicode_literals
import re
-from .common import InfoExtractor
-from ..utils import (
- parse_iso8601,
- int_or_none,
-)
+from .amp import AMPIE
-class FoxNewsIE(InfoExtractor):
+class FoxNewsIE(AMPIE):
IE_DESC = 'Fox News and Fox Business Video'
_VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
_TESTS = [
@@ -20,10 +16,10 @@ class FoxNewsIE(InfoExtractor):
'id': '3937480',
'ext': 'flv',
'title': 'Frozen in Time',
- 'description': 'Doctors baffled by 16-year-old girl that is the size of a toddler',
+ 'description': '16-year-old girl is size of toddler',
'duration': 265,
- 'timestamp': 1304411491,
- 'upload_date': '20110503',
+ # 'timestamp': 1304411491,
+ # 'upload_date': '20110503',
'thumbnail': 're:^https?://.*\.jpg$',
},
},
@@ -34,10 +30,10 @@ class FoxNewsIE(InfoExtractor):
'id': '3922535568001',
'ext': 'mp4',
'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal",
- 'description': "Congressman discusses the president's executive action",
+ 'description': "Congressman discusses president's plan",
'duration': 292,
- 'timestamp': 1417662047,
- 'upload_date': '20141204',
+ # 'timestamp': 1417662047,
+ # 'upload_date': '20141204',
'thumbnail': 're:^https?://.*\.jpg$',
},
},
@@ -52,52 +48,9 @@ class FoxNewsIE(InfoExtractor):
]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
- host = mobj.group('host')
+ host, video_id = re.match(self._VALID_URL, url).groups()
- video = self._download_json(
- 'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id), video_id)
-
- item = video['channel']['item']
- title = item['title']
- description = item['description']
- timestamp = parse_iso8601(item['dc-date'])
-
- media_group = item['media-group']
- duration = None
- formats = []
- for media in media_group['media-content']:
- attributes = media['@attributes']
- video_url = attributes['url']
- if video_url.endswith('.f4m'):
- formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', video_id))
- elif video_url.endswith('.m3u8'):
- formats.extend(self._extract_m3u8_formats(video_url, video_id, 'flv'))
- elif not video_url.endswith('.smil'):
- duration = int_or_none(attributes.get('duration'))
- formats.append({
- 'url': video_url,
- 'format_id': media['media-category']['@attributes']['label'],
- 'preference': 1,
- 'vbr': int_or_none(attributes.get('bitrate')),
- 'filesize': int_or_none(attributes.get('fileSize'))
- })
- self._sort_formats(formats)
-
- media_thumbnail = media_group['media-thumbnail']['@attributes']
- thumbnails = [{
- 'url': media_thumbnail['url'],
- 'width': int_or_none(media_thumbnail.get('width')),
- 'height': int_or_none(media_thumbnail.get('height')),
- }] if media_thumbnail else []
-
- return {
- 'id': video_id,
- 'title': title,
- 'description': description,
- 'duration': duration,
- 'timestamp': timestamp,
- 'formats': formats,
- 'thumbnails': thumbnails,
- }
+ info = self._extract_feed_info(
+ 'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
+ info['id'] = video_id
+ return info
