Merge pull request #4 from debian-janitor/lintian-fixes

[youtubedl] / youtube_dl / extractor / tvigle.py

diff --git a/youtube_dl/extractor/tvigle.py b/youtube_dl/extractor/tvigle.py
index 102362b295450f58ff085ec9be7d21921a1ac494..180259abac795e3f27e221c6c0cb95afdfe768ec 100644 (file)
--- a/youtube_dl/extractor/tvigle.py
+++ b/youtube_dl/extractor/tvigle.py
@@ -1,12 +1,16 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
 from ..utils import (
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
 from ..utils import (

+    ExtractorError,

     float_or_none,
     float_or_none,

+    int_or_none,

     parse_age_limit,
     parse_age_limit,

+    try_get,
+    url_or_none,

 )
 
 
 )
 
 


@@ -15,31 +19,34 @@ class TvigleIE(InfoExtractor):
     IE_DESC = 'Интернет-телевидение Tvigle.ru'
     _VALID_URL = r'https?://(?:www\.)?(?:tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$|cloud\.tvigle\.ru/video/(?P<id>\d+))'
 
     IE_DESC = 'Интернет-телевидение Tvigle.ru'
     _VALID_URL = r'https?://(?:www\.)?(?:tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$|cloud\.tvigle\.ru/video/(?P<id>\d+))'
 

+    _GEO_BYPASS = False
+    _GEO_COUNTRIES = ['RU']
+

     _TESTS = [
         {
             'url': 'http://www.tvigle.ru/video/sokrat/',
     _TESTS = [
         {
             'url': 'http://www.tvigle.ru/video/sokrat/',

-            'md5': '36514aed3657d4f70b4b2cef8eb520cd',

             'info_dict': {
                 'id': '1848932',
                 'display_id': 'sokrat',
             'info_dict': {
                 'id': '1848932',
                 'display_id': 'sokrat',

-                'ext': 'flv',
+                'ext': 'mp4',

                 'title': 'Сократ',
                 'title': 'Сократ',

-                'description': 'md5:a05bd01be310074d5833efc6743be95e',
+                'description': 'md5:d6b92ffb7217b4b8ebad2e7665253c17',

                 'duration': 6586,
                 'duration': 6586,

-                'age_limit': 0,
+                'age_limit': 12,

             },
             },

+            'skip': 'georestricted',

         },
         {
             'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/',
         },
         {
             'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/',

-            'md5': 'd9012d7c7c598fe7a11d7fb46dc1f574',

             'info_dict': {
                 'id': '5142516',
             'info_dict': {
                 'id': '5142516',

-                'ext': 'mp4',
+                'ext': 'flv',

                 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком',
                 'description': 'md5:027f7dc872948f14c96d19b4178428a4',
                 'duration': 186.080,
                 'age_limit': 0,
             },
                 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком',
                 'description': 'md5:027f7dc872948f14c96d19b4178428a4',
                 'duration': 186.080,
                 'age_limit': 0,
             },

+            'skip': 'georestricted',

         }, {
             'url': 'https://cloud.tvigle.ru/video/5267604/',
             'only_matching': True,
         }, {
             'url': 'https://cloud.tvigle.ru/video/5267604/',
             'only_matching': True,


@@ -54,7 +61,9 @@ class TvigleIE(InfoExtractor):
         if not video_id:
             webpage = self._download_webpage(url, display_id)
             video_id = self._html_search_regex(
         if not video_id:
             webpage = self._download_webpage(url, display_id)
             video_id = self._html_search_regex(

-                r'<li class="video-preview current_playing" id="(\d+)">',
+                (r'<div[^>]+class=["\']player["\'][^>]+id=["\'](\d+)',
+                 r'cloudId\s*=\s*["\'](\d+)',
+                 r'class="video-preview current_playing" id="(\d+)"'),

                 webpage, 'video id')
 
         video_data = self._download_json(
                 webpage, 'video id')
 
         video_data = self._download_json(


@@ -62,22 +71,59 @@ class TvigleIE(InfoExtractor):
 
         item = video_data['playlist']['items'][0]
 
 
         item = video_data['playlist']['items'][0]
 

+        videos = item.get('videos')
+
+        error_message = item.get('errorMessage')
+        if not videos and error_message:
+            if item.get('isGeoBlocked') is True:
+                self.raise_geo_restricted(
+                    msg=error_message, countries=self._GEO_COUNTRIES)
+            else:
+                raise ExtractorError(
+                    '%s returned error: %s' % (self.IE_NAME, error_message),
+                    expected=True)
+

         title = item['title']
         title = item['title']

-        description = item['description']
-        thumbnail = item['thumbnail']
+        description = item.get('description')
+        thumbnail = item.get('thumbnail')

         duration = float_or_none(item.get('durationMilliseconds'), 1000)
         age_limit = parse_age_limit(item.get('ageRestrictions'))
 
         formats = []
         duration = float_or_none(item.get('durationMilliseconds'), 1000)
         age_limit = parse_age_limit(item.get('ageRestrictions'))
 
         formats = []

-        for vcodec, fmts in item['videos'].items():
-            for quality, video_url in fmts.items():
-                formats.append({
-                    'url': video_url,
-                    'format_id': '%s-%s' % (vcodec, quality),
-                    'vcodec': vcodec,
-                    'height': int(quality[:-1]),
-                    'filesize': item['video_files_size'][vcodec][quality],
-                })
+        for vcodec, url_or_fmts in item['videos'].items():
+            if vcodec == 'hls':
+                m3u8_url = url_or_none(url_or_fmts)
+                if not m3u8_url:
+                    continue
+                formats.extend(self._extract_m3u8_formats(
+                    m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            elif vcodec == 'dash':
+                mpd_url = url_or_none(url_or_fmts)
+                if not mpd_url:
+                    continue
+                formats.extend(self._extract_mpd_formats(
+                    mpd_url, video_id, mpd_id='dash', fatal=False))
+            else:
+                if not isinstance(url_or_fmts, dict):
+                    continue
+                for format_id, video_url in url_or_fmts.items():
+                    if format_id == 'm3u8':
+                        continue
+                    video_url = url_or_none(video_url)
+                    if not video_url:
+                        continue
+                    height = self._search_regex(
+                        r'^(\d+)[pP]$', format_id, 'height', default=None)
+                    filesize = int_or_none(try_get(
+                        item, lambda x: x['video_files_size'][vcodec][format_id]))
+                    formats.append({
+                        'url': video_url,
+                        'format_id': '%s-%s' % (vcodec, format_id),
+                        'vcodec': vcodec,
+                        'height': int_or_none(height),
+                        'filesize': filesize,
+                    })

         self._sort_formats(formats)
 
         return {
         self._sort_formats(formats)
 
         return {