Update upstream source from tag 'upstream/2019.09.28'

[youtubedl] / youtube_dl / extractor / tvigle.py

diff --git a/youtube_dl/extractor/tvigle.py b/youtube_dl/extractor/tvigle.py
index dc3a8334a6b335143dff417d805a26df412d8783..180259abac795e3f27e221c6c0cb95afdfe768ec 100644 (file)
--- a/youtube_dl/extractor/tvigle.py
+++ b/youtube_dl/extractor/tvigle.py
@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re


@@ -9,6 +9,8 @@ from ..utils import (
     float_or_none,
     int_or_none,
     parse_age_limit,
     float_or_none,
     int_or_none,
     parse_age_limit,

+    try_get,
+    url_or_none,

 )
 
 
 )
 
 


@@ -17,14 +19,16 @@ 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',
                 'description': 'md5:d6b92ffb7217b4b8ebad2e7665253c17',
                 'duration': 6586,
                 'title': 'Сократ',
                 'description': 'md5:d6b92ffb7217b4b8ebad2e7665253c17',
                 'duration': 6586,


@@ -34,7 +38,6 @@ class TvigleIE(InfoExtractor):
         },
         {
             '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': 'e7efe5350dd5011d0de6550b53c3ba7b',

             'info_dict': {
                 'id': '5142516',
                 'ext': 'flv',
             'info_dict': {
                 'id': '5142516',
                 'ext': 'flv',


@@ -58,7 +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'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(


@@ -70,8 +75,13 @@ class TvigleIE(InfoExtractor):
 
         error_message = item.get('errorMessage')
         if not videos and error_message:
 
         error_message = item.get('errorMessage')
         if not videos and error_message:

-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
+            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']
         description = item.get('description')
 
         title = item['title']
         description = item.get('description')


@@ -80,21 +90,40 @@ class TvigleIE(InfoExtractor):
         age_limit = parse_age_limit(item.get('ageRestrictions'))
 
         formats = []
         age_limit = parse_age_limit(item.get('ageRestrictions'))
 
         formats = []

-        for vcodec, fmts in item['videos'].items():
-            for format_id, video_url in fmts.items():
-                if format_id == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        video_url, video_id, 'mp4', m3u8_id=vcodec))
+        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
                     continue

-                height = self._search_regex(
-                    r'^(\d+)[pP]$', format_id, 'height', default=None)
-                formats.append({
-                    'url': video_url,
-                    'format_id': '%s-%s' % (vcodec, format_id),
-                    'vcodec': vcodec,
-                    'height': int_or_none(height),
-                    'filesize': int_or_none(item.get('video_files_size', {}).get(vcodec, {}).get(format_id)),
-                })
+                for format_id, video_url in url_or_fmts.items():
+                    if format_id == 'm3u8':
+                        continue
+                    video_url = url_or_none(video_url)
+                    if not video_url:
+                        continue
+                    height = self._search_regex(
+                        r'^(\d+)[pP]$', 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 {