From 9150d1eb6936e7f3ad168095f57dc0c8f56d2364 Mon Sep 17 00:00:00 2001 From: Sergey M․ Date: Fri, 10 Feb 2017 01:03:35 +0700 Subject: [xtube] Fix extraction (closes #12023) --- youtube_dl/extractor/xtube.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'youtube_dl/extractor/xtube.py') diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 83bc1fef2..91bae7ee7 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -60,7 +60,8 @@ class XTubeIE(InfoExtractor): webpage = self._download_webpage(req, display_id) sources = self._parse_json(self._search_regex( - r'sources\s*:\s*({.+?}),', webpage, 'sources'), video_id) + r'(["\'])sources\1\s*:\s*(?P{.+?}),', + webpage, 'sources', group='sources'), video_id) formats = [] for format_id, format_url in sources.items(): @@ -81,10 +82,10 @@ class XTubeIE(InfoExtractor): r']+class="nickname"[^>]*>([^<]+)'), webpage, 'uploader', fatal=False) duration = parse_duration(self._search_regex( - r'
Runtime:
\s*
([^<]+)
', + r'
Runtime:?
\s*
([^<]+)
', webpage, 'duration', fatal=False)) view_count = str_to_int(self._search_regex( - r'
Views:
\s*
([\d,\.]+)
', + r'
Views:?
\s*
([\d,\.]+)
', webpage, 'view count', fatal=False)) comment_count = str_to_int(self._html_search_regex( r'>Comments? \(([\d,\.]+)\)<', -- cgit 1.4.1 From fbc6dc525e525565544b377a1d16cd915cb11a7c Mon Sep 17 00:00:00 2001 From: Sergey M․ Date: Fri, 10 Feb 2017 01:05:48 +0700 Subject: [xtube] Fix shortcuts --- youtube_dl/extractor/xtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'youtube_dl/extractor/xtube.py') diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 91bae7ee7..11717fe98 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -53,7 +53,7 @@ class XTubeIE(InfoExtractor): if not display_id: display_id = video_id - url = 'http://www.xtube.com/watch.php?v=%s' % video_id + url = 'http://www.xtube.com/video-watch/-%s' % video_id req = sanitized_Request(url) req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1') -- cgit 1.4.1 From f6d6ca1db3020e7c7771880d0c4b58fdf732a8d5 Mon Sep 17 00:00:00 2001 From: Vobe Date: Sat, 11 Feb 2017 21:11:55 +0100 Subject: [xtube] Improve title extraction --- youtube_dl/extractor/xtube.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'youtube_dl/extractor/xtube.py') diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 11717fe98..ed3a37649 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -53,7 +53,7 @@ class XTubeIE(InfoExtractor): if not display_id: display_id = video_id - url = 'http://www.xtube.com/video-watch/-%s' % video_id + url = 'http://www.xtube.com/watch.php?v=%s' % video_id req = sanitized_Request(url) req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1') @@ -73,7 +73,7 @@ class XTubeIE(InfoExtractor): self._sort_formats(formats) title = self._search_regex( - (r'

(?P[^<]+)</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), + (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), webpage, 'title', group='title') description = self._search_regex( r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False) -- cgit 1.4.1 From 085f169ffebc17ec8b2bfc63aec8f5df57c7bdcf Mon Sep 17 00:00:00 2001 From: Sergey M․ <dstftw@gmail.com> Date: Mon, 13 Feb 2017 23:44:43 +0700 Subject: [xtube] Fix extraction for both kinds of video id (closes #12088) --- youtube_dl/extractor/xtube.py | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'youtube_dl/extractor/xtube.py') diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index ed3a37649..5584674a0 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -44,6 +44,9 @@ class XTubeIE(InfoExtractor): }, { 'url': 'xtube:625837', 'only_matching': True, + }, { + 'url': 'xtube:kVTUy_G222_', + 'only_matching': True, }] def _real_extract(self, url): @@ -53,11 +56,16 @@ class XTubeIE(InfoExtractor): if not display_id: display_id = video_id - url = 'http://www.xtube.com/watch.php?v=%s' % video_id - req = sanitized_Request(url) - req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1') - webpage = self._download_webpage(req, display_id) + if video_id.isdigit() and len(video_id) < 11: + url_pattern = 'http://www.xtube.com/video-watch/-%s' + else: + url_pattern = 'http://www.xtube.com/watch.php?v=%s' + + webpage = self._download_webpage( + url_pattern % video_id, display_id, headers={ + 'Cookie': 'age_verified=1; cookiesAccepted=1', + }) sources = self._parse_json(self._search_regex( r'(["\'])sources\1\s*:\s*(?P<sources>{.+?}),', -- cgit 1.4.1 From 24eb7c257807aceef713f6d01824cf600a9d6232 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan <yan12125@gmail.com> Date: Sat, 29 Apr 2017 15:55:08 +0800 Subject: [xtube] Fix extraction with non-standard JSON 'sources' Closes #12734 Thanks @paulguy for the fix! --- ChangeLog | 6 ++++++ youtube_dl/extractor/xtube.py | 23 +++++++++++++++++++++-- 2 files changed, 27 insertions(+), 2 deletions(-) (limited to 'youtube_dl/extractor/xtube.py') diff --git a/ChangeLog b/ChangeLog index cd49ac42d..aa7543325 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +version <unreleased> + +Extractors +* [xtube] Fix extraction for older FLV videos (#12734) + + version 2017.04.28 Core diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 5584674a0..bea9b87ad 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -6,6 +6,7 @@ import re from .common import InfoExtractor from ..utils import ( int_or_none, + js_to_json, orderedSet, parse_duration, sanitized_Request, @@ -37,6 +38,22 @@ class XTubeIE(InfoExtractor): 'comment_count': int, 'age_limit': 18, } + }, { + # FLV videos with duplicated formats + 'url': 'http://www.xtube.com/video-watch/A-Super-Run-Part-1-YT-9299752', + 'md5': 'a406963eb349dd43692ec54631efd88b', + 'info_dict': { + 'id': '9299752', + 'display_id': 'A-Super-Run-Part-1-YT', + 'ext': 'flv', + 'title': 'A Super Run - Part 1 (YT)', + 'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93', + 'uploader': 'tshirtguy59', + 'duration': 579, + 'view_count': int, + 'comment_count': int, + 'age_limit': 18, + }, }, { # new URL schema 'url': 'http://www.xtube.com/video-watch/strange-erotica-625837', @@ -68,8 +85,9 @@ class XTubeIE(InfoExtractor): }) sources = self._parse_json(self._search_regex( - r'(["\'])sources\1\s*:\s*(?P<sources>{.+?}),', - webpage, 'sources', group='sources'), video_id) + r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),', + webpage, 'sources', group='sources'), video_id, + transform_source=js_to_json) formats = [] for format_id, format_url in sources.items(): @@ -78,6 +96,7 @@ class XTubeIE(InfoExtractor): 'format_id': format_id, 'height': int_or_none(format_id), }) + self._remove_duplicate_formats(formats) self._sort_formats(formats) title = self._search_regex( -- cgit 1.4.1 From ac93c09ab2c4d099a628c1ed59670bef008db89c Mon Sep 17 00:00:00 2001 From: Sergey M․ <dstftw@gmail.com> Date: Fri, 6 Oct 2017 23:53:32 +0700 Subject: [xtube] Add support for embedded URLs (closes #14417) --- youtube_dl/extractor/xtube.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'youtube_dl/extractor/xtube.py') diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index bea9b87ad..c6c0b3291 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -18,7 +18,7 @@ class XTubeIE(InfoExtractor): _VALID_URL = r'''(?x) (?: xtube:| - https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?P<display_id>[^/]+)-) + https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?:embedded/)?(?P<display_id>[^/]+)-) ) (?P<id>[^/?&#]+) ''' @@ -64,6 +64,9 @@ class XTubeIE(InfoExtractor): }, { 'url': 'xtube:kVTUy_G222_', 'only_matching': True, + }, { + 'url': 'https://www.xtube.com/video-watch/embedded/milf-tara-and-teen-shared-and-cum-covered-extreme-bukkake-32203482?embedsize=big', + 'only_matching': True, }] def _real_extract(self, url): -- cgit 1.4.1