Updated version 2017.10.15.1 from 'upstream/2017.10.15.1'

[youtubedl] / youtube_dl / extractor / itv.py

diff --git a/youtube_dl/extractor/itv.py b/youtube_dl/extractor/itv.py
index b0d8604526abc29b4b0a09eb59068561f17312a8..26c48e4b889545f4e2ffacccfdb859678c4bf2c3 100644 (file)
--- a/youtube_dl/extractor/itv.py
+++ b/youtube_dl/extractor/itv.py
@@ -24,6 +24,7 @@ from ..utils import (
 
 class ITVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'
 
 class ITVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'

+    _GEO_COUNTRIES = ['GB']

     _TEST = {
         'url': 'http://www.itv.com/hub/mr-bean-animated-series/2a2936a0053',
         'info_dict': {
     _TEST = {
         'url': 'http://www.itv.com/hub/mr-bean-animated-series/2a2936a0053',
         'info_dict': {


@@ -58,12 +59,18 @@ class ITVIE(InfoExtractor):
         def _add_sub_element(element, name):
             return etree.SubElement(element, _add_ns(name))
 
         def _add_sub_element(element, name):
             return etree.SubElement(element, _add_ns(name))
 

+        production_id = (
+            params.get('data-video-autoplay-id') or
+            '%s#001' % (
+                params.get('data-video-episode-id') or
+                video_id.replace('a', '/')))
+

         req_env = etree.Element(_add_ns('soapenv:Envelope'))
         _add_sub_element(req_env, 'soapenv:Header')
         body = _add_sub_element(req_env, 'soapenv:Body')
         get_playlist = _add_sub_element(body, ('tem:GetPlaylist'))
         request = _add_sub_element(get_playlist, 'tem:request')
         req_env = etree.Element(_add_ns('soapenv:Envelope'))
         _add_sub_element(req_env, 'soapenv:Header')
         body = _add_sub_element(req_env, 'soapenv:Body')
         get_playlist = _add_sub_element(body, ('tem:GetPlaylist'))
         request = _add_sub_element(get_playlist, 'tem:request')

-        _add_sub_element(request, 'itv:ProductionId').text = params['data-video-id']
+        _add_sub_element(request, 'itv:ProductionId').text = production_id

         _add_sub_element(request, 'itv:RequestGuid').text = compat_str(uuid.uuid4()).upper()
         vodcrid = _add_sub_element(request, 'itv:Vodcrid')
         _add_sub_element(vodcrid, 'com:Id')
         _add_sub_element(request, 'itv:RequestGuid').text = compat_str(uuid.uuid4()).upper()
         vodcrid = _add_sub_element(request, 'itv:Vodcrid')
         _add_sub_element(vodcrid, 'com:Id')


@@ -98,7 +105,11 @@ class ITVIE(InfoExtractor):
             headers=headers, data=etree.tostring(req_env))
         playlist = xpath_element(resp_env, './/Playlist')
         if playlist is None:
             headers=headers, data=etree.tostring(req_env))
         playlist = xpath_element(resp_env, './/Playlist')
         if playlist is None:

+            fault_code = xpath_text(resp_env, './/faultcode')

             fault_string = xpath_text(resp_env, './/faultstring')
             fault_string = xpath_text(resp_env, './/faultstring')

+            if fault_code == 'InvalidGeoRegion':
+                self.raise_geo_restricted(
+                    msg=fault_string, countries=self._GEO_COUNTRIES)

             raise ExtractorError('%s said: %s' % (self.IE_NAME, fault_string))
         title = xpath_text(playlist, 'EpisodeTitle', fatal=True)
         video_element = xpath_element(playlist, 'VideoEntries/Video', fatal=True)
             raise ExtractorError('%s said: %s' % (self.IE_NAME, fault_string))
         title = xpath_text(playlist, 'EpisodeTitle', fatal=True)
         video_element = xpath_element(playlist, 'VideoEntries/Video', fatal=True)


@@ -111,13 +122,25 @@ class ITVIE(InfoExtractor):
             if not play_path:
                 continue
             tbr = int_or_none(media_file.get('bitrate'), 1000)
             if not play_path:
                 continue
             tbr = int_or_none(media_file.get('bitrate'), 1000)

-            formats.append({
+            f = {

                 'format_id': 'rtmp' + ('-%d' % tbr if tbr else ''),
                 'format_id': 'rtmp' + ('-%d' % tbr if tbr else ''),

-                'url': rtmp_url,

                 'play_path': play_path,
                 'play_path': play_path,

+                # Providing this swfVfy allows to avoid truncated downloads
+                'player_url': 'http://www.itv.com/mercury/Mercury_VideoPlayer.swf',
+                'page_url': url,

                 'tbr': tbr,
                 'ext': 'flv',
                 'tbr': tbr,
                 'ext': 'flv',

-            })
+            }
+            app = self._search_regex(
+                'rtmpe?://[^/]+/(.+)$', rtmp_url, 'app', default=None)
+            if app:
+                f.update({
+                    'url': rtmp_url.split('?', 1)[0],
+                    'app': app,
+                })
+            else:
+                f['url'] = rtmp_url
+            formats.append(f)

 
         ios_playlist_url = params.get('data-video-playlist')
         hmac = params.get('data-video-hmac')
 
         ios_playlist_url = params.get('data-video-playlist')
         hmac = params.get('data-video-hmac')


@@ -167,7 +190,9 @@ class ITVIE(InfoExtractor):
                         href = ios_base_url + href
                     ext = determine_ext(href)
                     if ext == 'm3u8':
                         href = ios_base_url + href
                     ext = determine_ext(href)
                     if ext == 'm3u8':

-                        formats.extend(self._extract_m3u8_formats(href, video_id, 'mp4', m3u8_id='hls', fatal=False))
+                        formats.extend(self._extract_m3u8_formats(
+                            href, video_id, 'mp4', entry_protocol='m3u8_native',
+                            m3u8_id='hls', fatal=False))

                     else:
                         formats.append({
                             'url': href,
                     else:
                         formats.append({
                             'url': href,


@@ -184,7 +209,8 @@ class ITVIE(InfoExtractor):
                 'ext': 'ttml' if ext == 'xml' else ext,
             })
 
                 'ext': 'ttml' if ext == 'xml' else ext,
             })
 

-        return {
+        info = self._search_json_ld(webpage, video_id, default={})
+        info.update({

             'id': video_id,
             'title': title,
             'formats': formats,
             'id': video_id,
             'title': title,
             'formats': formats,


@@ -193,4 +219,5 @@ class ITVIE(InfoExtractor):
             'episode_number': int_or_none(xpath_text(playlist, 'EpisodeNumber')),
             'series': xpath_text(playlist, 'ProgrammeTitle'),
             'duartion': parse_duration(xpath_text(playlist, 'Duration')),
             'episode_number': int_or_none(xpath_text(playlist, 'EpisodeNumber')),
             'series': xpath_text(playlist, 'ProgrammeTitle'),
             'duartion': parse_duration(xpath_text(playlist, 'Duration')),

-        }
+        })
+        return info