Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-29 19:47:54 +01:00
Code Issues Releases Wiki Activity

[hhu] Don't place closing braces/brackets/parentheses on their own lines

Browse Source
This commit is contained in:
Niklas Sombert 2019-10-09 20:04:51 +02:00
parent 9f07fb2382
commit 233400f3d9
1 changed files with 19 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
youtube_dl/extractor/hhu.py
View File

@ -26,15 +26,12 @@ class HHUIE(InfoExtractor):
'UKD', 'eLearning', 'Abstimmsysteme', 'Portale',
'Studierendenportal', 'Lehrfilme', 'Lehrfilm',
'Operationsfilme', 'Vorlesungsaufzeichnung', 'Multimedia',
'ZIM', 'HHU', 'Ute', 'Clames', # yes, that's incorrect
],
'ZIM', 'HHU', 'Ute', 'Clames', ], # yes, that's incorrect
'uploader': 'clames',
'uploader_id': 'clames',
'license': 'CC BY 3.0 DE',
'upload_date': '20150126',
'thumbnail': 'https://mediathek.hhu.de/thumbs/2dd05982-ea45-4108-9620-0c36e6ed8df5/thumb_000.jpg',
}
}
'thumbnail': 'https://mediathek.hhu.de/thumbs/2dd05982-ea45-4108-9620-0c36e6ed8df5/thumb_000.jpg', }}
def _real_extract(self, url):
video_id = self._match_id(url)
@ -44,30 +41,25 @@ class HHUIE(InfoExtractor):
# Some videos need a login, maybe TODO.
try:
config_js = self._search_regex(
r'playerInstance\.setup\(([^;]+)\);', webpage, 'config_js'
)
r'playerInstance\.setup\(([^;]+)\);', webpage, 'config_js')
# remove 'link: encodeURI("<our url>"),'
if 'link: encodeURI' in config_js:
encode_begin = config_js.find('link: encodeURI')
encode_end = config_js.find(')', encode_begin)
config_js = (
config_js[:encode_begin] + config_js[encode_end + 2:]
)
config_js[:encode_begin] + config_js[encode_end + 2:])
del encode_begin, encode_end
config = json.loads(js_to_json(config_js))
if len(config['playlist']) > 1:
self.report_warning(
'more than one video, just taking the first one'
)
'more than one video, just taking the first one')
video = config['playlist'][0]
formats = [
{
'url': urljoin('https://mediathek.hhu.de/', source['file']),
'format_note': source.get('label'),
'format_id': source['file'].split("/")[-1],
}
for source in video['sources']
]
'format_id': source['file'].split("/")[-1], }
for source in video['sources']]
formats.reverse() # config sorts from highest to lowest quality
title = video.get('title')
thumbnail = video.get('image')
@ -78,8 +70,7 @@ class HHUIE(InfoExtractor):
# This will likely work but better warn.
file_id = self._html_search_regex(
r"{ file: '\/movies\/(.+?)\/v_100\.mp4', label: '",
webpage, 'file_id'
)
webpage, 'file_id')
formats = [
({'url': format_url.format(file_id)})
for format_url in (
@ -88,54 +79,43 @@ class HHUIE(InfoExtractor):
'https://mediathek.hhu.de/movies/{}/v_50.webm',
'https://mediathek.hhu.de/movies/{}/v_50.mp4',
'https://mediathek.hhu.de/movies/{}/v_100.webm',
'https://mediathek.hhu.de/movies/{}/v_100.mp4',
)
]
'https://mediathek.hhu.de/movies/{}/v_100.mp4',)]
title = thumbnail = None
if not title:
title = self._html_search_regex(
r'<h1 id="mt_watch-headline-title">\s+(.+?)\s+<\/h1>',
webpage, 'title'
)
webpage, 'title')
if not title:
title = self._og_search_title(webpage, fatal=False)
description = self._html_search_regex(
r'<p id="mt_watch-description" class="watch-description">\s+(.+?)\s+<\/p>',
webpage, 'description', fatal=False
)
webpage, 'description', fatal=False)
if not description:
description = self._og_search_description(webpage, default='')
if not thumbnail:
thumbnail = self._og_search_property(
'image:secure_url', webpage, 'thumbnail', fatal=False
)
'image:secure_url', webpage, 'thumbnail', fatal=False)
uploader = self._html_search_regex(
r'<a id="mt_content_placeholder_videoinfo_createdby" class="author" href=".+">(.+?)<\/a>',
webpage, 'uploader', fatal=False
)
webpage, 'uploader', fatal=False)
uploader_id = self._html_search_regex(
r'<a id="mt_content_placeholder_videoinfo_createdby" class="author" href="/user/(.+)">.+?<\/a>',
webpage, 'uploader_id', fatal=False
)
webpage, 'uploader_id', fatal=False)
# CC licenses get a image with an appropriate alt text
license_img = get_element_by_id('mt_watch_license', webpage)
if license_img:
license = self._search_regex(
r'alt="(.+)"', license_img, 'license_img', fatal=False
)
r'alt="(.+)"', license_img, 'license_img', fatal=False)
if not license_img or not license:
# other licenses are just text
license = self._html_search_regex(
r'<div id="mt_content_placeholder_videotabs_mt_videotabs_formview_video_license" class="video-license">(.+)<\/div>',
webpage, 'license_text', fatal=False
)
webpage, 'license_text', fatal=False)
upload_date = _date(self._html_search_regex(
r'<span class="watch-information-date added">(.+?)<\/span>',
webpage, 'upload_date', fatal=False
))
webpage, 'upload_date', fatal=False))
category = self._html_search_regex(
r'<a href="/category/.+">(.+)</a>', webpage, 'category', fatal=False
)
r'<a href="/category/.+">(.+)</a>', webpage, 'category', fatal=False)
tags_html = get_element_by_id('mt_watch_info_tag_list', webpage)
tags = _tags(tags_html)
@ -150,8 +130,7 @@ class HHUIE(InfoExtractor):
'uploader_id': uploader_id,
'upload_date': upload_date,
'thumbnail': thumbnail,
'formats': formats,
}
'formats': formats, }
def _date(str_containing_date):