Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-24 01:14:32 +01:00
Code Issues Releases Wiki Activity

[intldropout] support multiple pages on playlists

Browse Source
This commit is contained in:
Thomas Tsiakalakis 2019-05-08 17:14:35 +02:00
parent e53f2ee17f
commit 6ef0a6268b
1 changed files with 18 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
youtube_dl/extractor/intldropout.py
View File

@ -71,30 +71,30 @@ class IntlDropoutPlaylistIE(IntlDropoutIE):
_VALID_URL = r'https://intl\.dropout\.tv/(?P<id>.+)' _VALID_URL = r'https://intl\.dropout\.tv/(?P<id>.+)'
_TESTS = [ _TESTS = [
{ {
'url': 'https://intl.dropout.tv/um-actually-the-web-series', 'url': 'https://intl.dropout.tv/um-actually',
'md5': 'ebcd26ef54f546225e7cb96e79da31cc', 'md5': 'ebcd26ef54f546225e7cb96e79da31cc',
'playlist_count': 9, 'playlist_count': 30,
'info_dict': { 'info_dict': {
'id': 'um-actually-the-web-series', 'id': 'um-actually',
'title': 'Um, Actually: The Web Series', 'title': 'Um, Actually',
} }
}, },
{ {
'url': 'https://intl.dropout.tv/new-releases', 'url': 'https://intl.dropout.tv/new-releases',
'md5': 'ebcd26ef54f546225e7cb96e79da31cc', 'md5': 'ebcd26ef54f546225e7cb96e79da31cc',
'playlist_count': 22, 'playlist_count': 24,
'info_dict': { 'info_dict': {
'id': 'new-releases', 'id': 'new-releases',
'title': 'New Releases', 'title': 'New Releases',
} }
}, },
{ {
'url': 'https://intl.dropout.tv/troopers/season:2', 'url': 'https://intl.dropout.tv/troopers-the-web-series/season:2',
'md5': 'ebcd26ef54f546225e7cb96e79da31cc', 'md5': 'ebcd26ef54f546225e7cb96e79da31cc',
'playlist_count': 10, 'playlist_count': 10,
'info_dict': { 'info_dict': {
'id': 'troopers/season:2', 'id': 'troopers-the-web-series/season:2',
'title': 'Troopers', 'title': 'Troopers: The Web Series',
} }
} }
] ]
@ -106,6 +106,14 @@ class IntlDropoutPlaylistIE(IntlDropoutIE):
def _real_extract(self, url): def _real_extract(self, url):
playlist_id = self._match_id(url) playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id) webpage = self._download_webpage(url, playlist_id)
items = re.findall(r'browse-item-title[^>]+>[^<]*<a href="(?P<url>https://intl.dropout.tv/[^/]+/[^"]+)"', webpage)
playlist_title = self._html_search_regex(r'<h1 class="[^"]*collection-title[^"]*"[^>]*>(?P<title>[^<]+)<', webpage, 'title') playlist_title = self._html_search_regex(r'<h1 class="[^"]*collection-title[^"]*"[^>]*>(?P<title>[^<]+)<', webpage, 'title')
items = []
while True:
items.extend(re.findall(r'browse-item-title[^>]+>[^<]*<a href="(?P<url>https://intl.dropout.tv/[^/]+/[^"]+)"', webpage))
next_page_url = self._search_regex(r'href="(/[^\?]+\?page=\d+)"', webpage, 'next page url', default=None)
if not next_page_url:
break
webpage = self._download_webpage('https://intl.dropout.tv' + next_page_url, playlist_id)
return self.playlist_from_matches(items, playlist_id=playlist_id, playlist_title=playlist_title) return self.playlist_from_matches(items, playlist_id=playlist_id, playlist_title=playlist_title)