Merge remote-tracking branch 'Boris-de/wdrmaus_fix#8562'

[youtube-dl] / youtube_dl / extractor / openload.py

diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py
index 71021d573f1fbe7af75b278a9ed519cb73f02517..5049b870ed198f3ce4f702c07efe98559d453ef2 100644 (file)
--- a/youtube_dl/extractor/openload.py
+++ b/youtube_dl/extractor/openload.py
@@ -5,21 +5,38 @@ import re
 
 from .common import InfoExtractor
 from ..compat import compat_chr
-from ..utils import encode_base_n
+from ..utils import (
+    determine_ext,
+    encode_base_n,
+    ExtractorError,
+    mimetype2ext,
+)
 
 
 class OpenloadIE(InfoExtractor):
-    _VALID_URL = r'https://openload.co/f/(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https://openload.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-]+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'https://openload.co/f/kUEfGclsU9o',
         'md5': 'bf1c059b004ebc7a256f89408e65c36e',
         'info_dict': {
             'id': 'kUEfGclsU9o',
             'ext': 'mp4',
             'title': 'skyrim_no-audio_1080.mp4',
+            'thumbnail': 're:^https?://.*\.jpg$',
         },
-    }
+    }, {
+        'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
+        'only_matching': True,
+    }, {
+        'url': 'https://openload.io/f/ZAn6oz-VZGE/',
+        'only_matching': True,
+    }, {
+        # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
+        # for title and ext
+        'url': 'https://openload.co/embed/Sxz5sADo82g/',
+        'only_matching': True,
+    }]
 
     @staticmethod
     def openload_level2_debase(m):
@@ -78,15 +95,33 @@ class OpenloadIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
+
+        if 'File not found' in webpage:
+            raise ExtractorError('File not found', expected=True)
+
         code = self._search_regex(
-            r'<video[^>]+>\s*<script[^>]+>([^<]+)</script>',
+            r'</video>\s*</div>\s*<script[^>]+>([^<]+)</script>',
             webpage, 'JS code')
 
+        decoded = self.openload_decode(code)
+
         video_url = self._search_regex(
-            r'return\s+"(https?://[^"]+)"', self.openload_decode(code), 'video URL')
+            r'return\s+"(https?://[^"]+)"', decoded, 'video URL')
+
+        title = self._og_search_title(webpage, default=None) or self._search_regex(
+            r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
+            'title', default=None) or self._html_search_meta(
+            'description', webpage, 'title', fatal=True)
+
+        ext = mimetype2ext(self._search_regex(
+            r'window\.vt\s*=\s*(["\'])(?P<mimetype>.+?)\1', decoded,
+            'mimetype', default=None, group='mimetype')) or determine_ext(
+            video_url, 'mp4')
 
         return {
             'id': video_id,
-            'title': self._og_search_title(webpage),
+            'title': title,
+            'ext': ext,
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'url': video_url,
         }