mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-09-10 00:58:17 +02:00
[niconico] Fix extraction and update tests (closes #5511)
This commit is contained in:
parent
9ee53a49f0
commit
bb865f3a5e
@ -14,7 +14,9 @@
|
|||||||
ExtractorError,
|
ExtractorError,
|
||||||
int_or_none,
|
int_or_none,
|
||||||
parse_duration,
|
parse_duration,
|
||||||
unified_strdate,
|
parse_iso8601,
|
||||||
|
xpath_text,
|
||||||
|
determine_ext,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
@ -32,6 +34,7 @@ class NiconicoIE(InfoExtractor):
|
|||||||
'uploader': 'takuya0301',
|
'uploader': 'takuya0301',
|
||||||
'uploader_id': '2698420',
|
'uploader_id': '2698420',
|
||||||
'upload_date': '20131123',
|
'upload_date': '20131123',
|
||||||
|
'timestamp': 1385182762,
|
||||||
'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
|
'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
|
||||||
'duration': 33,
|
'duration': 33,
|
||||||
},
|
},
|
||||||
@ -46,16 +49,31 @@ class NiconicoIE(InfoExtractor):
|
|||||||
'id': 'nm14296458',
|
'id': 'nm14296458',
|
||||||
'ext': 'swf',
|
'ext': 'swf',
|
||||||
'title': '【鏡音リン】Dance on media【オリジナル】take2!',
|
'title': '【鏡音リン】Dance on media【オリジナル】take2!',
|
||||||
'description': 'md5:',
|
'description': 'md5:689f066d74610b3b22e0f1739add0f58',
|
||||||
'uploader': 'りょうた',
|
'uploader': 'りょうた',
|
||||||
'uploader_id': '18822557',
|
'uploader_id': '18822557',
|
||||||
'upload_date': '20110429',
|
'upload_date': '20110429',
|
||||||
|
'timestamp': 1304065916,
|
||||||
'duration': 209,
|
'duration': 209,
|
||||||
},
|
},
|
||||||
'params': {
|
'params': {
|
||||||
'username': 'ydl.niconico@gmail.com',
|
'username': 'ydl.niconico@gmail.com',
|
||||||
'password': 'youtube-dl',
|
'password': 'youtube-dl',
|
||||||
},
|
},
|
||||||
|
}, {
|
||||||
|
# 'video exists but is marked as "deleted"
|
||||||
|
'url': 'http://www.nicovideo.jp/watch/sm10000',
|
||||||
|
'md5': '38e53c9aad548f3ecf01ca7680b59b08',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'sm10000',
|
||||||
|
'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>',
|
||||||
|
},
|
||||||
|
'params': {
|
||||||
|
'username': 'ydl.niconico@gmail.com',
|
||||||
|
'password': 'youtube-dl',
|
||||||
|
}
|
||||||
}]
|
}]
|
||||||
|
|
||||||
_VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
|
_VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
|
||||||
@ -95,9 +113,10 @@ def _login(self):
|
|||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
|
|
||||||
# Get video webpage. We are not actually interested in it, but need
|
# Get video webpage. We are not actually interested in it for normal
|
||||||
# the cookies in order to be able to download the info webpage
|
# cases, but need the cookies in order to be able to download the
|
||||||
self._download_webpage('http://www.nicovideo.jp/watch/' + video_id, video_id)
|
# info webpage
|
||||||
|
webpage = self._download_webpage('http://www.nicovideo.jp/watch/' + video_id, video_id)
|
||||||
|
|
||||||
video_info = self._download_xml(
|
video_info = self._download_xml(
|
||||||
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
|
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
|
||||||
@ -127,22 +146,34 @@ def _real_extract(self, url):
|
|||||||
flv_info_request, video_id,
|
flv_info_request, video_id,
|
||||||
note='Downloading flv info', errnote='Unable to download flv info')
|
note='Downloading flv info', errnote='Unable to download flv info')
|
||||||
|
|
||||||
if 'deleted=' in flv_info_webpage:
|
flv_info = compat_urlparse.parse_qs(flv_info_webpage)
|
||||||
raise ExtractorError('The video has been deleted.',
|
if 'url' not in flv_info:
|
||||||
expected=True)
|
if 'deleted' in flv_info:
|
||||||
video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
|
raise ExtractorError('The video has been deleted.',
|
||||||
|
expected=True)
|
||||||
|
else:
|
||||||
|
raise ExtractorError('Unable to find video URL')
|
||||||
|
|
||||||
|
video_real_url = flv_info['url'][0]
|
||||||
|
|
||||||
# Start extracting information
|
# Start extracting information
|
||||||
title = video_info.find('.//title').text
|
title = xpath_text(video_info, './/title')
|
||||||
extension = video_info.find('.//movie_type').text
|
if not title:
|
||||||
|
title = self._html_search_regex(
|
||||||
|
r'<span[^>]+class="videoHeaderTitle"[^>]*>([^<]+)</span>',
|
||||||
|
webpage, 'video title')
|
||||||
|
|
||||||
|
extension = xpath_text(video_info, './/movie_type')
|
||||||
|
if not extension:
|
||||||
|
extension = determine_ext(video_real_url)
|
||||||
video_format = extension.upper()
|
video_format = extension.upper()
|
||||||
thumbnail = video_info.find('.//thumbnail_url').text
|
thumbnail = xpath_text(video_info, './/thumbnail_url')
|
||||||
description = video_info.find('.//description').text
|
description = xpath_text(video_info, './/description')
|
||||||
upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0])
|
timestamp = parse_iso8601(xpath_text(video_info, './/first_retrieve'))
|
||||||
view_count = int_or_none(video_info.find('.//view_counter').text)
|
view_count = int_or_none(xpath_text(video_info, './/view_counter'))
|
||||||
comment_count = int_or_none(video_info.find('.//comment_num').text)
|
comment_count = int_or_none(xpath_text(video_info, './/comment_num'))
|
||||||
duration = parse_duration(video_info.find('.//length').text)
|
duration = parse_duration(xpath_text(video_info, './/length'))
|
||||||
webpage_url = video_info.find('.//watch_url').text
|
webpage_url = xpath_text(video_info, './/watch_url')
|
||||||
|
|
||||||
if video_info.find('.//ch_id') is not None:
|
if video_info.find('.//ch_id') is not None:
|
||||||
uploader_id = video_info.find('.//ch_id').text
|
uploader_id = video_info.find('.//ch_id').text
|
||||||
@ -153,7 +184,7 @@ def _real_extract(self, url):
|
|||||||
else:
|
else:
|
||||||
uploader_id = uploader = None
|
uploader_id = uploader = None
|
||||||
|
|
||||||
return {
|
ret = {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'url': video_real_url,
|
'url': video_real_url,
|
||||||
'title': title,
|
'title': title,
|
||||||
@ -162,13 +193,14 @@ def _real_extract(self, url):
|
|||||||
'thumbnail': thumbnail,
|
'thumbnail': thumbnail,
|
||||||
'description': description,
|
'description': description,
|
||||||
'uploader': uploader,
|
'uploader': uploader,
|
||||||
'upload_date': upload_date,
|
'timestamp': timestamp,
|
||||||
'uploader_id': uploader_id,
|
'uploader_id': uploader_id,
|
||||||
'view_count': view_count,
|
'view_count': view_count,
|
||||||
'comment_count': comment_count,
|
'comment_count': comment_count,
|
||||||
'duration': duration,
|
'duration': duration,
|
||||||
'webpage_url': webpage_url,
|
'webpage_url': webpage_url,
|
||||||
}
|
}
|
||||||
|
return dict((k, v) for k, v in ret.items() if v is not None)
|
||||||
|
|
||||||
|
|
||||||
class NiconicoPlaylistIE(InfoExtractor):
|
class NiconicoPlaylistIE(InfoExtractor):
|
||||||
|
Loading…
Reference in New Issue
Block a user