mirror of
https://gitlab.com/ytdl-org/youtube-dl.git
synced 2026-04-27 00:00:04 -04:00
Compare commits
10 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 6ed99754bb | |||
| 0e7dfa7d16 | |||
| baba5f4d1d | |||
| dee04d24a4 | |||
| 5b3ddadcc3 | |||
| 5b232f46dc | |||
| 4bf22f7a10 | |||
| 15d1e8a23d | |||
| ee6a611665 | |||
| 463e7216c8 |
@@ -6,8 +6,8 @@
|
||||
|
||||
---
|
||||
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.08.06*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
|
||||
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.08.06**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.08.09*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
|
||||
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.08.09**
|
||||
|
||||
### Before submitting an *issue* make sure you have:
|
||||
- [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
|
||||
@@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
|
||||
[debug] User config: []
|
||||
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
|
||||
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
|
||||
[debug] youtube-dl version 2017.08.06
|
||||
[debug] youtube-dl version 2017.08.09
|
||||
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
|
||||
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
|
||||
[debug] Proxy map: {}
|
||||
|
||||
@@ -1,3 +1,18 @@
|
||||
version 2017.08.09
|
||||
|
||||
Core
|
||||
* [utils] Skip missing params in cli_bool_option (#13865)
|
||||
|
||||
Extractors
|
||||
* [xxxymovies] Fix title extraction (#13868)
|
||||
+ [nick] Add support for nick.com.pl (#13860)
|
||||
* [mixcloud] Fix play info decryption (#13867)
|
||||
* [20min] Fix embeds extraction (#13852)
|
||||
* [dplayit] Fix extraction (#13851)
|
||||
+ [niconico] Support videos with multiple formats (#13522)
|
||||
+ [niconico] Support HTML5-only videos (#13806)
|
||||
|
||||
|
||||
version 2017.08.06
|
||||
|
||||
Core
|
||||
|
||||
@@ -1182,6 +1182,10 @@ part 3</font></u>
|
||||
cli_bool_option(
|
||||
{'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
|
||||
['--check-certificate=true'])
|
||||
self.assertEqual(
|
||||
cli_bool_option(
|
||||
{}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
|
||||
[])
|
||||
|
||||
def test_ohdave_rsa_encrypt(self):
|
||||
N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
|
||||
|
||||
@@ -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),
|
||||
|
||||
@@ -54,15 +54,22 @@ class MixcloudIE(InfoExtractor):
|
||||
}]
|
||||
|
||||
# See https://www.mixcloud.com/media/js2/www_js_2.9e23256562c080482435196ca3975ab5.js
|
||||
@staticmethod
|
||||
def _decrypt_play_info(play_info):
|
||||
KEY = 'pleasedontdownloadourmusictheartistswontgetpaid'
|
||||
|
||||
def _decrypt_play_info(self, play_info, video_id):
|
||||
KEYS = (
|
||||
'pleasedontdownloadourmusictheartistswontgetpaid',
|
||||
'(function() { return new Date().toLocaleDateString(); })()'
|
||||
)
|
||||
play_info = base64.b64decode(play_info.encode('ascii'))
|
||||
|
||||
return ''.join([
|
||||
compat_chr(compat_ord(ch) ^ compat_ord(KEY[idx % len(KEY)]))
|
||||
for idx, ch in enumerate(play_info)])
|
||||
for num, key in enumerate(KEYS, start=1):
|
||||
try:
|
||||
return self._parse_json(
|
||||
''.join([
|
||||
compat_chr(compat_ord(ch) ^ compat_ord(key[idx % len(key)]))
|
||||
for idx, ch in enumerate(play_info)]),
|
||||
video_id)
|
||||
except ExtractorError:
|
||||
if num == len(KEYS):
|
||||
raise
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
@@ -78,8 +85,8 @@ class MixcloudIE(InfoExtractor):
|
||||
|
||||
encrypted_play_info = self._search_regex(
|
||||
r'm-play-info="([^"]+)"', webpage, 'play info')
|
||||
play_info = self._parse_json(
|
||||
self._decrypt_play_info(encrypted_play_info), track_id)
|
||||
|
||||
play_info = self._decrypt_play_info(encrypted_play_info, track_id)
|
||||
|
||||
if message and 'stream_url' not in play_info:
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
|
||||
|
||||
@@ -75,7 +75,7 @@ class NickIE(MTVServicesInfoExtractor):
|
||||
|
||||
class NickDeIE(MTVServicesInfoExtractor):
|
||||
IE_NAME = 'nick.de'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<host>nick\.de|nickelodeon\.(?:nl|at))/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<host>nick\.(?:de|com\.pl)|nickelodeon\.(?:nl|at))/[^/]+/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.nick.de/playlist/3773-top-videos/videos/episode/17306-zu-wasser-und-zu-land-rauchende-erdnusse',
|
||||
'only_matching': True,
|
||||
@@ -88,6 +88,9 @@ class NickDeIE(MTVServicesInfoExtractor):
|
||||
}, {
|
||||
'url': 'http://www.nickelodeon.at/playlist/3773-top-videos/videos/episode/77993-das-letzte-gefecht',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.nick.com.pl/seriale/474-spongebob-kanciastoporty/wideo/17412-teatr-to-jest-to-rodeo-oszolom',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _extract_mrss_url(self, webpage, host):
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -50,7 +50,7 @@ class TwentyMinutenIE(InfoExtractor):
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return [m.group('url') for m in re.finditer(
|
||||
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:www\.)?20min\.ch/videoplayer/videoplayer.html\?.*?\bvideoId@\d+.*?)\1',
|
||||
r'<iframe[^>]+src=(["\'])(?P<url>(?:(?:https?:)?//)?(?:www\.)?20min\.ch/videoplayer/videoplayer.html\?.*?\bvideoId@\d+.*?)\1',
|
||||
webpage)]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@@ -39,8 +39,8 @@ class XXXYMoviesIE(InfoExtractor):
|
||||
r"video_url\s*:\s*'([^']+)'", webpage, 'video URL')
|
||||
|
||||
title = self._html_search_regex(
|
||||
[r'<div class="block_header">\s*<h1>([^<]+)</h1>',
|
||||
r'<title>(.*?)\s*-\s*XXXYMovies\.com</title>'],
|
||||
[r'<div[^>]+\bclass="block_header"[^>]*>\s*<h1>([^<]+)<',
|
||||
r'<title>(.*?)\s*-\s*(?:XXXYMovies\.com|XXX\s+Movies)</title>'],
|
||||
webpage, 'title')
|
||||
|
||||
thumbnail = self._search_regex(
|
||||
|
||||
@@ -2733,6 +2733,8 @@ def cli_option(params, command_option, param):
|
||||
|
||||
def cli_bool_option(params, command_option, param, true_value='true', false_value='false', separator=None):
|
||||
param = params.get(param)
|
||||
if param is None:
|
||||
return []
|
||||
assert isinstance(param, bool)
|
||||
if separator:
|
||||
return [command_option + separator + (true_value if param else false_value)]
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2017.08.06'
|
||||
__version__ = '2017.08.09'
|
||||
|
||||
Reference in New Issue
Block a user