From 82e4eca711a128138ed0b84ddb4321e403d56340 Mon Sep 17 00:00:00 2001 From: Xiyue <113869642+xiyue077@users.noreply.github.com> Date: Tue, 11 Oct 2022 09:52:48 +1100 Subject: [PATCH] [motherless] Fixed the broken uploader_id in the extractor (#31243) * Fixed the broken uploader_id in the extractor. * Make uploader_id RE looser * Fix uploader_id in test Motherless_3 * Fix group pagination * # coding: utf-8 Co-authored-by: Andy Xuming Co-authored-by: dirkf --- youtube_dl/extractor/motherless.py | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py index ef1e081f2..35d2b46ed 100644 --- a/youtube_dl/extractor/motherless.py +++ b/youtube_dl/extractor/motherless.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import datetime @@ -71,7 +72,7 @@ class MotherlessIE(InfoExtractor): 'title': 'a/ Hot Teens', 'categories': list, 'upload_date': '20210104', - 'uploader_id': 'yonbiw', + 'uploader_id': 'anonymous', 'thumbnail': r're:https?://.*\.jpg', 'age_limit': 18, }, @@ -127,7 +128,7 @@ class MotherlessIE(InfoExtractor): comment_count = webpage.count('class="media-comment-contents"') uploader_id = self._html_search_regex( - r'"thumb-member-username">\s+]+>\s*]+\bhref\s*=\s*['"]/m/([^"']+)''', webpage, 'uploader_id') categories = self._html_search_meta('keywords', webpage, default=None) @@ -169,7 +170,7 @@ class MotherlessGroupIE(InfoExtractor): 'description': 'Sex can be funny. Wide smiles,laugh, games, fun of ' 'any kind!' }, - 'playlist_mincount': 9, + 'playlist_mincount': 0, }] @classmethod @@ -208,9 +209,9 @@ class MotherlessGroupIE(InfoExtractor): r'([\w\s]+\w)\s+-', webpage, 'title', fatal=False) description = self._html_search_meta( 'description', webpage, fatal=False) - page_count = self._int(self._search_regex( - r'(\d+)</(?:a|span)><(?:a|span)[^>]+>\s*NEXT', - webpage, 'page_count'), 'page_count') + page_count = str_to_int(self._search_regex( + r'(\d+)\s*</(?:a|span)>\s*<(?:a|span)[^>]+(?:>\s*NEXT|\brel\s*=\s*["\']?next)\b', + webpage, 'page_count', default='1')) PAGE_SIZE = 80 def _get_page(idx):