[indavideo] Fix extraction (closes #11221)

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

diff --git a/youtube_dl/extractor/indavideo.py b/youtube_dl/extractor/indavideo.py
index b7571524457d44eecc5b319f879220b9944d3929..2946c7b8416f6d97301a040094cf3dc941e5ca2d 100644 (file)
--- a/youtube_dl/extractor/indavideo.py
+++ b/youtube_dl/extractor/indavideo.py
@@ -1,12 +1,13 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .. import utils
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
     parse_age_limit,
     parse_iso8601,
+    update_url_query,
 )
 
 
@@ -14,13 +15,13 @@ class IndavideoEmbedIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:embed\.)?indavideo\.hu/player/video/|assets\.indavideo\.hu/swf/player\.swf\?.*\b(?:v(?:ID|id))=)(?P<id>[\da-f]+)'
     _TESTS = [{
         'url': 'http://indavideo.hu/player/video/1bdc3c6d80/',
-        'md5': 'f79b009c66194acacd40712a6778acfa',
+        'md5': 'c8a507a1c7410685f83a06eaeeaafeab',
         'info_dict': {
             'id': '1837039',
             'ext': 'mp4',
             'title': 'Cicatánc',
             'description': '',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'cukiajanlo',
             'uploader_id': '83729',
             'timestamp': 1439193826,
@@ -44,10 +45,16 @@ class IndavideoEmbedIE(InfoExtractor):
             'http://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/%s' % video_id,
             video_id)['data']
 
-        video_id = video['id']
         title = video['title']
 
-        video_urls = video.get('video_files', [])
+        video_urls = []
+
+        video_files = video.get('video_files')
+        if isinstance(video_files, list):
+            video_urls.extend(video_files)
+        elif isinstance(video_files, dict):
+            video_urls.extend(video_files.values())
+
         video_file = video.get('video_file')
         if video:
             video_urls.append(video_file)
@@ -60,10 +67,23 @@ class IndavideoEmbedIE(InfoExtractor):
             if flv_url not in video_urls:
                 video_urls.append(flv_url)
 
-        formats = [{
-            'url': video_url,
-            'height': self._search_regex(r'\.(\d{3,4})\.mp4$', video_url, 'height', default=None),
-        } for video_url in video_urls]
+        filesh = video.get('filesh')
+
+        formats = []
+        for video_url in video_urls:
+            height = int_or_none(self._search_regex(
+                r'\.(\d{3,4})\.mp4(?:\?|$)', video_url, 'height', default=None))
+            if filesh:
+                if not height:
+                    continue
+                token = filesh.get(compat_str(height))
+                if token is None:
+                    continue
+                video_url = update_url_query(video_url, {'token': token})
+            formats.append({
+                'url': video_url,
+                'height': height,
+            })
         self._sort_formats(formats)
 
         timestamp = video.get('date')
@@ -75,10 +95,10 @@ class IndavideoEmbedIE(InfoExtractor):
             'url': self._proto_relative_url(thumbnail)
         } for thumbnail in video.get('thumbnails', [])]
 
-        tags = [tag['title'] for tag in video.get('tags', [])]
+        tags = [tag['title'] for tag in video.get('tags') or []]
 
         return {
-            'id': video_id,
+            'id': video.get('id') or video_id,
             'title': title,
             'description': video.get('description'),
             'thumbnails': thumbnails,
@@ -93,8 +113,8 @@ class IndavideoEmbedIE(InfoExtractor):
 
 
 class IndavideoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?indavideo\.hu/video/(?P<id>[^/#?]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:.+?\.)?indavideo\.hu/video/(?P<id>[^/#?]+)'
+    _TESTS = [{
         'url': 'http://indavideo.hu/video/Vicces_cica_1',
         'md5': '8c82244ba85d2a2310275b318eb51eac',
         'info_dict': {
@@ -103,23 +123,40 @@ class IndavideoIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Vicces cica',
             'description': 'Játszik a tablettel. :D',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'Jet_Pack',
             'uploader_id': '491217',
             'timestamp': 1390821212,
             'upload_date': '20140127',
             'duration': 7,
             'age_limit': 0,
-            'tags': ['vicces', 'macska', 'cica', 'ügyes', 'nevetés', 'játszik', 'Cukiság', 'Jet_Pack'],
+            'tags': list,
         },
-    }
+    }, {
+        'url': 'http://index.indavideo.hu/video/2015_0728_beregszasz',
+        'only_matching': True,
+    }, {
+        'url': 'http://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko',
+        'only_matching': True,
+    }, {
+        'url': 'http://erotika.indavideo.hu/video/Amator_tini_punci',
+        'only_matching': True,
+    }, {
+        'url': 'http://film.indavideo.hu/video/f_hrom_nagymamm_volt',
+        'only_matching': True,
+    }, {
+        'url': 'http://palyazat.indavideo.hu/video/Embertelen_dal_Dodgem_egyuttes',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
         webpage = self._download_webpage(url, display_id)
         embed_url = self._search_regex(
-            r'<link[^>]+rel="video_src"[^>]+href="(.+?)"', webpage, 'embed url')
+            (r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.indavideo\.hu/player/video/.+?)\1',
+             r'<link[^>]+rel="video_src"[^>]+href="(?P<url>.+?)"'),
+            webpage, 'embed url', group='url')
 
         return {
             '_type': 'url_transparent',