From d2c5b5a951868ae974bc3af6659ab39b8abd2157 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Sat, 30 Dec 2017 05:52:35 +0700
Subject: [PATCH] [openload] Fallback on f-page extraction (closes #14665,
closes #14879)
---
youtube_dl/extractor/openload.py | 28 +++++++++++++++++++++-------
1 file changed, 21 insertions(+), 7 deletions(-)
diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py
index d1eb3be25..81c1317b6 100644
--- a/youtube_dl/extractor/openload.py
+++ b/youtube_dl/extractor/openload.py
@@ -284,6 +284,11 @@ class OpenloadIE(InfoExtractor):
# for title and ext
'url': 'https://openload.co/embed/Sxz5sADo82g/',
'only_matching': True,
+ }, {
+ # unavailable via https://openload.co/embed/e-Ixz9ZR5L0/ but available
+ # via https://openload.co/f/e-Ixz9ZR5L0/
+ 'url': 'https://openload.co/f/e-Ixz9ZR5L0/',
+ 'only_matching': True,
}, {
'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
'only_matching': True,
@@ -305,18 +310,27 @@ class OpenloadIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
- url = 'https://openload.co/embed/%s/' % video_id
+ url_pattern = 'https://openload.co/%%s/%s/' % video_id
headers = {
'User-Agent': self._USER_AGENT,
}
- webpage = self._download_webpage(url, video_id, headers=headers)
-
- if 'File not found' in webpage or 'deleted by the owner' in webpage:
- raise ExtractorError('File not found', expected=True, video_id=video_id)
+ for path in ('embed', 'f'):
+ page_url = url_pattern % path
+ last = path == 'f'
+ webpage = self._download_webpage(
+ page_url, video_id, 'Downloading %s webpage' % path,
+ headers=headers, fatal=last)
+ if not webpage:
+ continue
+ if 'File not found' in webpage or 'deleted by the owner' in webpage:
+ if not last:
+ continue
+ raise ExtractorError('File not found', expected=True, video_id=video_id)
+ break
phantom = PhantomJSwrapper(self, required_version='2.0')
- webpage, _ = phantom.get(url, html=webpage, video_id=video_id, headers=headers)
+ webpage, _ = phantom.get(page_url, html=webpage, video_id=video_id, headers=headers)
decoded_id = get_element_by_id('streamurl', webpage)
@@ -327,7 +341,7 @@ class OpenloadIE(InfoExtractor):
'title', default=None) or self._html_search_meta(
'description', webpage, 'title', fatal=True)
- entries = self._parse_html5_media_entries(url, webpage, video_id)
+ entries = self._parse_html5_media_entries(page_url, webpage, video_id)
entry = entries[0] if entries else {}
subtitles = entry.get('subtitles')