Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2025-02-17 01:17:54 +01:00
Code Issues Releases Wiki Activity

Reduce amount of variables

Browse Source
This commit is contained in:
aapjez 2020-10-02 03:13:09 +02:00
parent fdaae7c2a4
commit 4b4839cba6
1 changed files with 7 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
youtube_dl/extractor/boundhub.py
View File

@ -28,48 +28,36 @@ class BoundHubIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) webpage = self._download_webpage(url, self._match_id(url))
webpage = self._download_webpage(url, video_id)
# Parse duration # Parse duration
duration_text = self._search_regex(r'<span>\s*Duration:\s*<em>([\w ]*)</em>', webpage, 'duration_text', fatal=False) duration_text = self._search_regex(r'<span>\s*Duration:\s*<em>([\w ]*)</em>', webpage, 'duration_text', fatal=False)
minutes = self._html_search_regex(r'(\d*)min', duration_text, 'minutes', fatal=False) minutes = self._html_search_regex(r'(\d*)min', duration_text, 'minutes', fatal=False)
seconds = self._html_search_regex(r'(\d*)sec', duration_text, 'seconds', fatal=False) seconds = self._html_search_regex(r'(\d*)sec', duration_text, 'seconds', fatal=False)
duration = (int(minutes) * 60) + int(seconds)
# Parse views # Get uploader url
views_text = self._search_regex(r'<span>\s*Views:\s*<em>([\w ]*)</em>', webpage, 'views_text', fatal=False)
views = int_or_none(views_text.replace(' ', ''))
# Get uploader url and id
uploader_url = self._search_regex(r'<div\s*class=[\"\']username[\"\']>\s*<a href=[\"\']([^\"\']*)[\"\']', webpage, 'uploader_url', fatal=False) uploader_url = self._search_regex(r'<div\s*class=[\"\']username[\"\']>\s*<a href=[\"\']([^\"\']*)[\"\']', webpage, 'uploader_url', fatal=False)
uploader_id = self._html_search_regex(r'https?://(?:www\.)?boundhub\.com/members/(\d+)', uploader_url, 'uploader_id', fatal=False)
uploader_id = int_or_none(uploader_id)
# Get screenshots # Get screenshots
html_screenshots = self._search_regex(r'<div\s*class=[\"\']block-screenshots[\"\']>([\s\S]+?)</div>', webpage, 'html_screenshots', fatal=False)
regex_screenshots = r'<a href=[\"\']([^\"\']*)[\"\']'
thumbnails = list() thumbnails = list()
for match in re.findall(r'<a href=[\"\']([^\"\']*)[\"\']', self._search_regex(r'<div\s*class=[\"\']block-screenshots[\"\']>([\s\S]+?)</div>', webpage, 'html_screenshots', fatal=False)):
for match in re.findall(regex_screenshots, html_screenshots):
img = dict() img = dict()
img['url'] = match.rstrip('/') img['url'] = match.rstrip('/')
img['id'] = int_or_none(os.path.splitext(os.path.basename(img['url']))[0]) img['id'] = int_or_none(os.path.splitext(os.path.basename(img['url']))[0])
thumbnails.append(img) thumbnails.append(img)
return { return {
'id': video_id, 'id': self._match_id(url),
'title': self._search_regex(r'<div\s*class=[\"\']headline[\"\']>\s*<h2>(.*)</h2>', webpage, 'title', default=None) or self._og_search_title(webpage), 'title': self._search_regex(r'<div\s*class=[\"\']headline[\"\']>\s*<h2>(.*)</h2>', webpage, 'title', default=None) or self._og_search_title(webpage),
'url': self._search_regex(r'video_url: [\"\']([^\"\']*)[\"\']', webpage, 'url'), 'url': self._search_regex(r'video_url: [\"\']([^\"\']*)[\"\']', webpage, 'url'),
'description': self._search_regex(r'<div\s*class=[\"\']item[\"\']>\s*Description:\s*<em>(.*)<\/em>', webpage, 'description', fatal=False), 'description': self._search_regex(r'<div\s*class=[\"\']item[\"\']>\s*Description:\s*<em>(.*)<\/em>', webpage, 'description', fatal=False),
'display_id': self._html_search_regex(r'https?://(?:www\.)?boundhub\.com/videos/[0-9]+/([\w-]*)', url, 'display_id', fatal=False), 'display_id': self._html_search_regex(r'https?://(?:www\.)?boundhub\.com/videos/[0-9]+/([\w-]*)', url, 'display_id', fatal=False),
'duration': duration, 'duration': (int(minutes) * 60) + int(seconds),
'ext': self._html_search_regex(r'postfix:\s*[\"\']\.([^\"\']*)[\"\']', webpage, 'ext', fatal=False), 'ext': self._html_search_regex(r'postfix:\s*[\"\']\.([^\"\']*)[\"\']', webpage, 'ext', fatal=False),
'thumbnail': self._html_search_regex(r'preview_url:\s*[\"\']([^\"\']*)[\"\']', webpage, 'thumbnail', fatal=False), 'thumbnail': self._html_search_regex(r'preview_url:\s*[\"\']([^\"\']*)[\"\']', webpage, 'thumbnail', fatal=False),
'thumbnails': thumbnails, 'thumbnails': thumbnails,
'uploader': self._search_regex(r'<div\s*class=[\"\']username[\"\']>\s*<a.*>\s*(.*)\s*</a>', webpage, 'uploader', fatal=False), 'uploader': self._search_regex(r'<div\s*class=[\"\']username[\"\']>\s*<a.*>\s*(.*)\s*</a>', webpage, 'uploader', fatal=False),
'uploader_id': uploader_id, 'uploader_id': int_or_none(self._html_search_regex(r'https?://(?:www\.)?boundhub\.com/members/(\d+)', uploader_url, 'uploader_id', fatal=False)),
'uploader_url': uploader_url, 'uploader_url': uploader_url,
'views': views, 'views': int_or_none(self._search_regex(r'<span>\s*Views:\s*<em>([\w ]*)</em>', webpage, 'views_text', fatal=False).replace(' ', '')),
} }