R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'master' into GoogleDrive-issue-13619

Browse Source
This commit is contained in:
Parmjit Virk 2017-08-07 14:19:52 -05:00
commit 7b393043cc
3 changed files with 266 additions and 70 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
ChangeLog
View File

@ -1,3 +1,10 @@
version <unreleased>
Extractors
+ [niconico] Support videos with multiple formats (#13522)
+ [niconico] Support HTML5-only videos (#13806)
version 2017.08.06
Core

66
youtube_dl/extractor/dplay.py
View File

@ -7,16 +7,18 @@ import time
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
compat_HTTPError,
compat_str,
compat_urlparse,
)
from ..utils import (
USER_AGENTS,
ExtractorError,
int_or_none,
unified_strdate,
remove_end,
try_get,
unified_strdate,
update_url_query,
USER_AGENTS,
)
@ -183,28 +185,44 @@ class DPlayItIE(InfoExtractor):
webpage = self._download_webpage(url, display_id)
info_url = self._search_regex(
r'url\s*[:=]\s*["\']((?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)',
webpage, 'video id')
title = remove_end(self._og_search_title(webpage), ' | Dplay')
try:
info = self._download_json(
info_url, display_id, headers={
'Authorization': 'Bearer %s' % self._get_cookies(url).get(
'dplayit_token').value,
'Referer': url,
})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403):
info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
error = info['errors'][0]
if error.get('code') == 'access.denied.geoblocked':
self.raise_geo_restricted(
msg=error.get('detail'), countries=self._GEO_COUNTRIES)
raise ExtractorError(info['errors'][0]['detail'], expected=True)
raise
video_id = None
info = self._search_regex(
r'playback_json\s*:\s*JSON\.parse\s*\(\s*("(?:\\.|[^"\\])+?")',
webpage, 'playback JSON', default=None)
if info:
for _ in range(2):
info = self._parse_json(info, display_id, fatal=False)
if not info:
break
else:
video_id = try_get(info, lambda x: x['data']['id'])
if not info:
info_url = self._search_regex(
r'url\s*[:=]\s*["\']((?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)',
webpage, 'info url')
video_id = info_url.rpartition('/')[-1]
try:
info = self._download_json(
info_url, display_id, headers={
'Authorization': 'Bearer %s' % self._get_cookies(url).get(
'dplayit_token').value,
'Referer': url,
})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403):
info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
error = info['errors'][0]
if error.get('code') == 'access.denied.geoblocked':
self.raise_geo_restricted(
msg=error.get('detail'), countries=self._GEO_COUNTRIES)
raise ExtractorError(info['errors'][0]['detail'], expected=True)
raise
hls_url = info['data']['attributes']['streaming']['hls']['url']
@ -230,7 +248,7 @@ class DPlayItIE(InfoExtractor):
season_number = episode_number = upload_date = None
return {
'id': info_url.rpartition('/')[-1],
'id': compat_str(video_id or display_id),
'display_id': display_id,
'title': title,
'description': self._og_search_description(webpage),

263
youtube_dl/extractor/niconico.py
View File

@ -11,10 +11,15 @@ from ..compat import (
)
from ..utils import (
determine_ext,
dict_get,
ExtractorError,
int_or_none,
float_or_none,
parse_duration,
parse_iso8601,
remove_start,
try_get,
unified_timestamp,
urlencode_postdata,
xpath_text,
)
@ -31,12 +36,15 @@ class NiconicoIE(InfoExtractor):
'id': 'sm22312215',
'ext': 'mp4',
'title': 'Big Buck Bunny',
'thumbnail': r're:https?://.*',
'uploader': 'takuya0301',
'uploader_id': '2698420',
'upload_date': '20131123',
'timestamp': 1385182762,
'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
'duration': 33,
'view_count': int,
'comment_count': int,
},
'skip': 'Requires an account',
}, {
@ -48,6 +56,7 @@ class NiconicoIE(InfoExtractor):
'ext': 'swf',
'title': '【鏡音リン】Dance on media【オリジナル】take2!',
'description': 'md5:689f066d74610b3b22e0f1739add0f58',
'thumbnail': r're:https?://.*',
'uploader': 'りょうた',
'uploader_id': '18822557',
'upload_date': '20110429',
@ -64,9 +73,11 @@ class NiconicoIE(InfoExtractor):
'ext': 'unknown_video',
'description': 'deleted',
'title': 'ドラえもんエターナル第3話「決戦第3新東京市」＜前編＞',
'thumbnail': r're:https?://.*',
'upload_date': '20071224',
'timestamp': int, # timestamp field has different value if logged in
'duration': 304,
'view_count': int,
},
'skip': 'Requires an account',
}, {
@ -76,12 +87,51 @@ class NiconicoIE(InfoExtractor):
'ext': 'mp4',
'title': '【第1回】RADIOアニメロミックス ラブライブ！～のぞえりRadio Garden～',
'description': 'md5:b27d224bb0ff53d3c8269e9f8b561cf1',
'thumbnail': r're:https?://.*',
'timestamp': 1388851200,
'upload_date': '20140104',
'uploader': 'アニメロチャンネル',
'uploader_id': '312',
},
'skip': 'The viewing period of the video you were searching for has expired.',
}, {
# video not available via `getflv`; "old" HTML5 video
'url': 'http://www.nicovideo.jp/watch/sm1151009',
'md5': '8fa81c364eb619d4085354eab075598a',
'info_dict': {
'id': 'sm1151009',
'ext': 'mp4',
'title': 'マスターシステム本体内蔵のスペハリのメインテーマ（ＰＳＧ版）',
'description': 'md5:6ee077e0581ff5019773e2e714cdd0b7',
'thumbnail': r're:https?://.*',
'duration': 184,
'timestamp': 1190868283,
'upload_date': '20070927',
'uploader': 'denden2',
'uploader_id': '1392194',
'view_count': int,
'comment_count': int,
},
'skip': 'Requires an account',
}, {
# "New" HTML5 video
'url': 'http://www.nicovideo.jp/watch/sm31464864',
'md5': '351647b4917660986dc0fa8864085135',
'info_dict': {
'id': 'sm31464864',
'ext': 'mp4',
'title': '新作TVアニメ「戦姫絶唱シンフォギアAXZ」PV 最高画質',
'description': 'md5:e52974af9a96e739196b2c1ca72b5feb',
'timestamp': 1498514060,
'upload_date': '20170626',
'uploader': 'ゲス',
'uploader_id': '40826363',
'thumbnail': r're:https?://.*',
'duration': 198,
'view_count': int,
'comment_count': int,
},
'skip': 'Requires an account',
}, {
'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
'only_matching': True,
@ -119,6 +169,84 @@ class NiconicoIE(InfoExtractor):
self._downloader.report_warning('unable to log in: bad username or password')
return login_ok
def _extract_format_for_quality(self, api_data, video_id, audio_quality, video_quality):
def yesno(boolean):
return 'yes' if boolean else 'no'
session_api_data = api_data['video']['dmcInfo']['session_api']
session_api_endpoint = session_api_data['urls'][0]
format_id = '-'.join(map(lambda s: remove_start(s['id'], 'archive_'), [video_quality, audio_quality]))
session_response = self._download_json(
session_api_endpoint['url'], video_id,
query={'_format': 'json'},
headers={'Content-Type': 'application/json'},
note='Downloading JSON metadata for %s' % format_id,
data=json.dumps({
'session': {
'client_info': {
'player_id': session_api_data['player_id'],
},
'content_auth': {
'auth_type': session_api_data['auth_types'][session_api_data['protocols'][0]],
'content_key_timeout': session_api_data['content_key_timeout'],
'service_id': 'nicovideo',
'service_user_id': session_api_data['service_user_id']
},
'content_id': session_api_data['content_id'],
'content_src_id_sets': [{
'content_src_ids': [{
'src_id_to_mux': {
'audio_src_ids': [audio_quality['id']],
'video_src_ids': [video_quality['id']],
}
}]
}],
'content_type': 'movie',
'content_uri': '',
'keep_method': {
'heartbeat': {
'lifetime': session_api_data['heartbeat_lifetime']
}
},
'priority': session_api_data['priority'],
'protocol': {
'name': 'http',
'parameters': {
'http_parameters': {
'parameters': {
'http_output_download_parameters': {
'use_ssl': yesno(session_api_endpoint['is_ssl']),
'use_well_known_port': yesno(session_api_endpoint['is_well_known_port']),
}
}
}
}
},
'recipe_id': session_api_data['recipe_id'],
'session_operation_auth': {
'session_operation_auth_by_signature': {
'signature': session_api_data['signature'],
'token': session_api_data['token'],
}
},
'timing_constraint': 'unlimited'
}
}))
resolution = video_quality.get('resolution', {})
return {
'url': session_response['data']['session']['content_uri'],
'format_id': format_id,
'ext': 'mp4', # Session API are used in HTML5, which always serves mp4
'abr': float_or_none(audio_quality.get('bitrate'), 1000),
'vbr': float_or_none(video_quality.get('bitrate'), 1000),
'height': resolution.get('height'),
'width': resolution.get('width'),
}
def _real_extract(self, url):
video_id = self._match_id(url)
@ -130,33 +258,84 @@ class NiconicoIE(InfoExtractor):
if video_id.startswith('so'):
video_id = self._match_id(handle.geturl())
video_info = self._download_xml(
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
note='Downloading video info page')
api_data = self._parse_json(self._html_search_regex(
'data-api-data="([^"]+)"', webpage,
'API data', default='{}'), video_id)
# Get flv info
flv_info_webpage = self._download_webpage(
'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
video_id, 'Downloading flv info')
def _format_id_from_url(video_url):
return 'economy' if video_real_url.endswith('low') else 'normal'
flv_info = compat_urlparse.parse_qs(flv_info_webpage)
if 'url' not in flv_info:
if 'deleted' in flv_info:
raise ExtractorError('The video has been deleted.',
expected=True)
elif 'closed' in flv_info:
raise ExtractorError('Niconico videos now require logging in',
expected=True)
elif 'error' in flv_info:
raise ExtractorError('%s reports error: %s' % (
self.IE_NAME, flv_info['error'][0]), expected=True)
else:
raise ExtractorError('Unable to find video URL')
try:
video_real_url = api_data['video']['smileInfo']['url']
except KeyError: # Flash videos
# Get flv info
flv_info_webpage = self._download_webpage(
'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
video_id, 'Downloading flv info')
video_real_url = flv_info['url'][0]
flv_info = compat_urlparse.parse_qs(flv_info_webpage)
if 'url' not in flv_info:
if 'deleted' in flv_info:
raise ExtractorError('The video has been deleted.',
expected=True)
elif 'closed' in flv_info:
raise ExtractorError('Niconico videos now require logging in',
expected=True)
elif 'error' in flv_info:
raise ExtractorError('%s reports error: %s' % (
self.IE_NAME, flv_info['error'][0]), expected=True)
else:
raise ExtractorError('Unable to find video URL')
video_info_xml = self._download_xml(
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id,
video_id, note='Downloading video info page')
def get_video_info(items):
if not isinstance(items, list):
items = [items]
for item in items:
ret = xpath_text(video_info_xml, './/' + item)
if ret:
return ret
video_real_url = flv_info['url'][0]
extension = get_video_info('movie_type')
if not extension:
extension = determine_ext(video_real_url)
formats = [{
'url': video_real_url,
'ext': extension,
'format_id': _format_id_from_url(video_real_url),
}]
else:
formats = []
dmc_info = api_data['video'].get('dmcInfo')
if dmc_info: # "New" HTML5 videos
quality_info = dmc_info['quality']
for audio_quality in quality_info['audios']:
for video_quality in quality_info['videos']:
if not audio_quality['available'] or not video_quality['available']:
continue
formats.append(self._extract_format_for_quality(
api_data, video_id, audio_quality, video_quality))
self._sort_formats(formats)
else: # "Old" HTML5 videos
formats = [{
'url': video_real_url,
'ext': 'mp4',
'format_id': _format_id_from_url(video_real_url),
}]
def get_video_info(items):
return dict_get(api_data['video'], items)
# Start extracting information
title = xpath_text(video_info, './/title')
title = get_video_info('title')
if not title:
title = self._og_search_title(webpage, default=None)
if not title:
@ -170,18 +349,15 @@ class NiconicoIE(InfoExtractor):
watch_api_data = self._parse_json(watch_api_data_string, video_id) if watch_api_data_string else {}
video_detail = watch_api_data.get('videoDetail', {})
extension = xpath_text(video_info, './/movie_type')
if not extension:
extension = determine_ext(video_real_url)
thumbnail = (
xpath_text(video_info, './/thumbnail_url') or
get_video_info(['thumbnail_url', 'thumbnailURL']) or
self._html_search_meta('image', webpage, 'thumbnail', default=None) or
video_detail.get('thumbnail'))
description = xpath_text(video_info, './/description')
description = get_video_info('description')
timestamp = parse_iso8601(xpath_text(video_info, './/first_retrieve'))
timestamp = (parse_iso8601(get_video_info('first_retrieve')) or
unified_timestamp(get_video_info('postedDateTime')))
if not timestamp:
match = self._html_search_meta('datePublished', webpage, 'date published', default=None)
if match:
@ -191,7 +367,7 @@ class NiconicoIE(InfoExtractor):
video_detail['postedAt'].replace('/', '-'),
delimiter=' ', timezone=datetime.timedelta(hours=9))
view_count = int_or_none(xpath_text(video_info, './/view_counter'))
view_count = int_or_none(get_video_info(['view_counter', 'viewCount']))
if not view_count:
match = self._html_search_regex(
r'>Views: <strong[^>]*>([^<]+)</strong>',
@ -200,38 +376,33 @@ class NiconicoIE(InfoExtractor):
view_count = int_or_none(match.replace(',', ''))
view_count = view_count or video_detail.get('viewCount')
comment_count = int_or_none(xpath_text(video_info, './/comment_num'))
comment_count = (int_or_none(get_video_info('comment_num')) or
video_detail.get('commentCount') or
try_get(api_data, lambda x: x['thread']['commentCount']))
if not comment_count:
match = self._html_search_regex(
r'>Comments: <strong[^>]*>([^<]+)</strong>',
webpage, 'comment count', default=None)
if match:
comment_count = int_or_none(match.replace(',', ''))
comment_count = comment_count or video_detail.get('commentCount')
duration = (parse_duration(
xpath_text(video_info, './/length') or
get_video_info('length') or
self._html_search_meta(
'video:duration', webpage, 'video duration', default=None)) or
video_detail.get('length'))
video_detail.get('length') or
get_video_info('duration'))
webpage_url = xpath_text(video_info, './/watch_url') or url
webpage_url = get_video_info('watch_url') or url
if video_info.find('.//ch_id') is not None:
uploader_id = video_info.find('.//ch_id').text
uploader = video_info.find('.//ch_name').text
elif video_info.find('.//user_id') is not None:
uploader_id = video_info.find('.//user_id').text
uploader = video_info.find('.//user_nickname').text
else:
uploader_id = uploader = None
owner = api_data.get('owner', {})
uploader_id = get_video_info(['ch_id', 'user_id']) or owner.get('id')
uploader = get_video_info(['ch_name', 'user_nickname']) or owner.get('nickname')
return {
'id': video_id,
'url': video_real_url,
'title': title,
'ext': extension,
'format_id': 'economy' if video_real_url.endswith('low') else 'normal',
'formats': formats,
'thumbnail': thumbnail,
'description': description,
'uploader': uploader,