From ed835e1b8c23ad0191ea8b152afd068b92d5f767 Mon Sep 17 00:00:00 2001 From: YetAnotherGhost <59511257+YetAnotherGhost@users.noreply.github.com> Date: Sat, 4 Jan 2020 18:11:36 +0100 Subject: [PATCH 1/4] [eroprofile] Update regexes Fixes #23200. --- youtube_dl/extractor/eroprofile.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/eroprofile.py b/youtube_dl/extractor/eroprofile.py index c08643a17..b48b6e5de 100644 --- a/youtube_dl/extractor/eroprofile.py +++ b/youtube_dl/extractor/eroprofile.py @@ -80,9 +80,9 @@ class EroProfileIE(InfoExtractor): video_url = unescapeHTML(self._search_regex( r'([^<]+)', webpage, 'title') + r']*>([^<]+)', webpage, 'title') thumbnail = self._search_regex( - r'onclick="showVideoPlayer\(\)">.* Date: Sat, 4 Jan 2020 18:50:19 +0100 Subject: [PATCH 2/4] [eroprofile] Add old regexes back (Should be squashed into the previous commit) --- youtube_dl/extractor/eroprofile.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/eroprofile.py b/youtube_dl/extractor/eroprofile.py index b48b6e5de..3485c3649 100644 --- a/youtube_dl/extractor/eroprofile.py +++ b/youtube_dl/extractor/eroprofile.py @@ -80,9 +80,10 @@ class EroProfileIE(InfoExtractor): video_url = unescapeHTML(self._search_regex( r']*>([^<]+)', webpage, 'title') + [r']*>([^<]+)', r'Title:([^<]+)'], + webpage, 'title') thumbnail = self._search_regex( - r'
.*.* Date: Sat, 4 Jan 2020 19:27:19 +0100 Subject: [PATCH 3/4] [eroprofile] Make regex part non-greedy (Should be squashed into the previous commits) --- youtube_dl/extractor/eroprofile.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/eroprofile.py b/youtube_dl/extractor/eroprofile.py index 3485c3649..a4c8ef0c7 100644 --- a/youtube_dl/extractor/eroprofile.py +++ b/youtube_dl/extractor/eroprofile.py @@ -83,7 +83,7 @@ class EroProfileIE(InfoExtractor): [r']*>([^<]+)', r'Title:([^<]+)'], webpage, 'title') thumbnail = self._search_regex( - [r'
.*.*? Date: Sat, 4 Jan 2020 20:11:35 +0100 Subject: [PATCH 4/4] [eroprofile] Use _html_search_regex for thumbnail (Should be squashed into the previous commits) --- youtube_dl/extractor/eroprofile.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/eroprofile.py b/youtube_dl/extractor/eroprofile.py index a4c8ef0c7..01b0a40d0 100644 --- a/youtube_dl/extractor/eroprofile.py +++ b/youtube_dl/extractor/eroprofile.py @@ -82,7 +82,7 @@ class EroProfileIE(InfoExtractor): title = self._html_search_regex( [r']*>([^<]+)', r'Title:([^<]+)'], webpage, 'title') - thumbnail = self._search_regex( + thumbnail = self._html_search_regex( [r'
.*?