pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2025-01-21 02:40:10 +09:00
Code Issues Projects Releases Wiki Activity

Added playlist extraction functionality

Browse Source
This commit is contained in:
SpiderRider067 2020-12-30 20:21:37 -05:00 committed by GitHub
parent 1dcca5c300
commit ee1b02ab83
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 52 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
youtube_dl/extractor/tasvideos.py
View File

@ -1,8 +1,10 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor
import re import re
from .common import InfoExtractor
class TASVideosIE(InfoExtractor): class TASVideosIE(InfoExtractor):
_VALID_URL = r'http://tasvideos.org/(?P<id>\d+M)\.html' _VALID_URL = r'http://tasvideos.org/(?P<id>\d+M)\.html'
@ -11,7 +13,7 @@ class TASVideosIE(InfoExtractor):
'md5': '8dced25a575e853cec5533a887a8dcfc', 'md5': '8dced25a575e853cec5533a887a8dcfc',
'info_dict': { 'info_dict': {
'id': '4352M', 'id': '4352M',
'ext': 'mkv', 'ext': 'mp4',
'title': 'C64 L\'Abbaye des Morts', 'title': 'C64 L\'Abbaye des Morts',
} }
} }
@ -25,12 +27,11 @@ class TASVideosIE(InfoExtractor):
title = self._search_regex( title = self._search_regex(
r'<span title="Movie[^"]+">(?P<TITLE>[^<]+)<\/span>', webpage, r'<span title="Movie[^"]+">(?P<TITLE>[^<]+)<\/span>', webpage,
'title') 'title')
formats = [] formats = []
for url in video_urls: for url in video_urls:
format_entry = {'url': "http://www." + url} format_entry = {'url': 'http://www.' + url}
formats.append(format_entry) formats.append(format_entry)
self._sort_formats(formats) self._sort_formats(formats)
return { return {
@ -38,3 +39,49 @@ class TASVideosIE(InfoExtractor):
'title': title, 'title': title,
'formats': formats, 'formats': formats,
} }
class TASVideosPlaylistIE(InfoExtractor):
_VALID_URL = r'http://tasvideos.org/(?P<id>Movies-[^\.]*?)\.html'
_TEST = {
'url': 'http://tasvideos.org/Movies-Stars.html',
'info_dict': {
'id': 'Movies-Stars',
'title': 'TASVideos movies: Tier Stars',
},
'playlist_count': 114,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
playlist_title = self._search_regex(
r'<title>(?P<title>[^<]*)</title>', webpage, 'title')
video_entries = re.findall(
r'((?s)<table class="item".*?archive.*?<\/table)>', webpage)
entries = []
for entry in video_entries:
video_urls = re.findall(
r'<a [^>]+(?P<URL>archive\.org\/download[^<]+\.(?:mkv|mp4|avi))[^<]+<\/a>',
entry)
title = self._search_regex(
r'<span title="Movie[^"]+">(?P<title>[^<]+)<\/span>', entry,
'title')
video_id = self._search_regex(
r'id="movie_(?P<id>\d+)', entry, 'video id') + 'M'
formats = []
for url in video_urls:
format_entry = {'url': "http://www." + url}
formats.append(format_entry)
self._sort_formats(formats)
formats = {
'id': video_id,
'title': title,
'formats': formats,
}
entries.append(formats)
return self.playlist_result(entries, playlist_id, playlist_title)