Prepare to upload

[youtubedl] / youtube_dl / extractor / biobiochiletv.py

diff --git a/youtube_dl/extractor/biobiochiletv.py b/youtube_dl/extractor/biobiochiletv.py
index 1332281337b2b5d64d0b89eb7d257a11ebffee71..b92031c8ab6bac3c5d5135743dda5883de080855 100644 (file)
--- a/youtube_dl/extractor/biobiochiletv.py
+++ b/youtube_dl/extractor/biobiochiletv.py
@@ -2,11 +2,15 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

-from ..utils import remove_end
+from ..utils import (
+    ExtractorError,
+    remove_end,
+)
+from .rudo import RudoIE

 
 
 class BioBioChileTVIE(InfoExtractor):
 
 
 class BioBioChileTVIE(InfoExtractor):

-    _VALID_URL = r'https?://tv\.biobiochile\.cl/notas/(?:[^/]+/)+(?P<id>[^/]+)\.shtml'
+    _VALID_URL = r'https?://(?:tv|www)\.biobiochile\.cl/(?:notas|noticias)/(?:[^/]+/)+(?P<id>[^/]+)\.shtml'

 
     _TESTS = [{
         'url': 'http://tv.biobiochile.cl/notas/2015/10/21/sobre-camaras-y-camarillas-parlamentarias.shtml',
 
     _TESTS = [{
         'url': 'http://tv.biobiochile.cl/notas/2015/10/21/sobre-camaras-y-camarillas-parlamentarias.shtml',


@@ -15,9 +19,10 @@ class BioBioChileTVIE(InfoExtractor):
             'id': 'sobre-camaras-y-camarillas-parlamentarias',
             'ext': 'mp4',
             'title': 'Sobre Cámaras y camarillas parlamentarias',
             'id': 'sobre-camaras-y-camarillas-parlamentarias',
             'ext': 'mp4',
             'title': 'Sobre Cámaras y camarillas parlamentarias',

-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',

             'uploader': 'Fernando Atria',
         },
             'uploader': 'Fernando Atria',
         },

+        'skip': 'URL expired and redirected to http://www.biobiochile.cl/portada/bbtv/index.html',

     }, {
         # different uploader layout
         'url': 'http://tv.biobiochile.cl/notas/2016/03/18/natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades.shtml',
     }, {
         # different uploader layout
         'url': 'http://tv.biobiochile.cl/notas/2016/03/18/natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades.shtml',


@@ -26,12 +31,22 @@ class BioBioChileTVIE(InfoExtractor):
             'id': 'natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades',
             'ext': 'mp4',
             'title': 'Natalia Valdebenito repasa a diputado Hasbún: Pasó a la categoría de hablar brutalidades',
             'id': 'natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades',
             'ext': 'mp4',
             'title': 'Natalia Valdebenito repasa a diputado Hasbún: Pasó a la categoría de hablar brutalidades',

-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',

             'uploader': 'Piangella Obrador',
         },
         'params': {
             'skip_download': True,
         },
             'uploader': 'Piangella Obrador',
         },
         'params': {
             'skip_download': True,
         },

+        'skip': 'URL expired and redirected to http://www.biobiochile.cl/portada/bbtv/index.html',
+    }, {
+        'url': 'http://www.biobiochile.cl/noticias/bbtv/comentarios-bio-bio/2016/07/08/edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos.shtml',
+        'info_dict': {
+            'id': 'edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos',
+            'ext': 'mp4',
+            'uploader': '(none)',
+            'upload_date': '20160708',
+            'title': 'Edecanes del Congreso: Figuras decorativas que le cuestan muy caro a los chilenos',
+        },

     }, {
         'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml',
         'only_matching': True,
     }, {
         'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml',
         'only_matching': True,


@@ -45,42 +60,22 @@ class BioBioChileTVIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
 
         webpage = self._download_webpage(url, video_id)
 

-        title = remove_end(self._og_search_title(webpage), ' - BioBioChile TV')
+        rudo_url = RudoIE._extract_url(webpage)
+        if not rudo_url:
+            raise ExtractorError('No videos found')

 
 

-        file_url = self._search_regex(
-            r'loadFWPlayerVideo\([^,]+,\s*(["\'])(?P<url>.+?)\1',
-            webpage, 'file url', group='url')
-
-        base_url = self._search_regex(
-            r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*fileURL', webpage,
-            'base url', default='http://unlimited2-cl.digitalproserver.com/bbtv/',
-            group='url')
-
-        formats = self._extract_m3u8_formats(
-            '%s%s/playlist.m3u8' % (base_url, file_url), video_id, 'mp4',
-            entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
-        f = {
-            'url': '%s%s' % (base_url, file_url),
-            'format_id': 'http',
-            'protocol': 'http',
-            'preference': 1,
-        }
-        if formats:
-            f_copy = formats[-1].copy()
-            f_copy.update(f)
-            f = f_copy
-        formats.append(f)
-        self._sort_formats(formats)
+        title = remove_end(self._og_search_title(webpage), ' - BioBioChile TV')

 
         thumbnail = self._og_search_thumbnail(webpage)
         uploader = self._html_search_regex(
 
         thumbnail = self._og_search_thumbnail(webpage)
         uploader = self._html_search_regex(

-            r'<a[^>]+href=["\']https?://busca\.biobiochile\.cl/author[^>]+>(.+?)</a>',
+            r'<a[^>]+href=["\']https?://(?:busca|www)\.biobiochile\.cl/(?:lista/)?(?:author|autor)[^>]+>(.+?)</a>',

             webpage, 'uploader', fatal=False)
 
         return {
             webpage, 'uploader', fatal=False)
 
         return {

+            '_type': 'url_transparent',
+            'url': rudo_url,

             'id': video_id,
             'title': title,
             'thumbnail': thumbnail,
             'uploader': uploader,
             'id': video_id,
             'title': title,
             'thumbnail': thumbnail,
             'uploader': uploader,

-            'formats': formats,

         }
         }