Improve URL extraction

youtube_dl/extractor/adultswim.py

@@ -7,6 +7,7 @@
 from ..utils import (
     int_or_none,
     strip_or_none,
+    url_or_none,
 )
 
 
@@ -98,7 +99,7 @@ def _real_extract(self, url):
             if not video_id:
                 entries = []
                 for episode in video_data.get('archiveEpisodes', []):
-                    episode_url = episode.get('url')
+                    episode_url = url_or_none(episode.get('url'))
                     if not episode_url:
                         continue
                     entries.append(self.url_result(

youtube_dl/extractor/afreecatv.py

@@ -9,6 +9,7 @@
     determine_ext,
     ExtractorError,
     int_or_none,
+    url_or_none,
     urlencode_postdata,
     xpath_text,
 )
@@ -304,7 +305,7 @@ def _real_extract(self, url):
             file_elements = video_element.findall(compat_xpath('./file'))
             one = len(file_elements) == 1
             for file_num, file_element in enumerate(file_elements, start=1):
-                file_url = file_element.text
+                file_url = url_or_none(file_element.text)
                 if not file_url:
                     continue
                 key = file_element.get('key', '')

youtube_dl/extractor/amp.py

@@ -3,11 +3,12 @@
 
 from .common import InfoExtractor
 from ..utils import (
-    int_or_none,
-    parse_iso8601,
-    mimetype2ext,
     determine_ext,
     ExtractorError,
+    int_or_none,
+    mimetype2ext,
+    parse_iso8601,
+    url_or_none,
 )
 
 
@@ -35,7 +36,7 @@ def get_media_node(name, default=None):
                 media_thumbnail = [media_thumbnail]
             for thumbnail_data in media_thumbnail:
                 thumbnail = thumbnail_data.get('@attributes', {})
-                thumbnail_url = thumbnail.get('url')
+                thumbnail_url = url_or_none(thumbnail.get('url'))
                 if not thumbnail_url:
                     continue
                 thumbnails.append({
@@ -51,7 +52,7 @@ def get_media_node(name, default=None):
                 media_subtitle = [media_subtitle]
             for subtitle_data in media_subtitle:
                 subtitle = subtitle_data.get('@attributes', {})
-                subtitle_href = subtitle.get('href')
+                subtitle_href = url_or_none(subtitle.get('href'))
                 if not subtitle_href:
                     continue
                 subtitles.setdefault(subtitle.get('lang') or 'en', []).append({
@@ -65,7 +66,7 @@ def get_media_node(name, default=None):
             media_content = [media_content]
         for media_data in media_content:
             media = media_data.get('@attributes', {})
-            media_url = media.get('url')
+            media_url = url_or_none(media.get('url'))
             if not media_url:
                 continue
             ext = mimetype2ext(media.get('type')) or determine_ext(media_url)
@@ -79,7 +80,7 @@ def get_media_node(name, default=None):
             else:
                 formats.append({
                     'format_id': media_data.get('media-category', {}).get('@attributes', {}).get('label'),
-                    'url': media['url'],
+                    'url': media_url,
                     'tbr': int_or_none(media.get('bitrate')),
                     'filesize': int_or_none(media.get('fileSize')),
                     'ext': ext,

youtube_dl/extractor/animeondemand.py

@@ -8,6 +8,7 @@
     determine_ext,
     extract_attributes,
     ExtractorError,
+    url_or_none,
     urlencode_postdata,
     urljoin,
 )
@@ -165,7 +166,7 @@ def extract_info(html, video_id, num=None):
                         }, fatal=False)
                     if not playlist:
                         continue
-                    stream_url = playlist.get('streamurl')
+                    stream_url = url_or_none(playlist.get('streamurl'))
                     if stream_url:
                         rtmp = re.search(
                             r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+/))(?P<playpath>mp[34]:.+)',

youtube_dl/extractor/aol.py

@@ -7,6 +7,7 @@
 from ..utils import (
     ExtractorError,
     int_or_none,
+    url_or_none,
 )
 
 
@@ -77,7 +78,7 @@ def _real_extract(self, url):
             formats.extend(self._extract_m3u8_formats(
                 m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
         for rendition in video_data.get('renditions', []):
-            video_url = rendition.get('url')
+            video_url = url_or_none(rendition.get('url'))
             if not video_url:
                 continue
             ext = rendition.get('format')

youtube_dl/extractor/apa.py

@@ -4,10 +4,10 @@
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     determine_ext,
     js_to_json,
+    url_or_none,
 )
 
 
@@ -68,8 +68,8 @@ def _real_extract(self, url):
         for source in sources:
             if not isinstance(source, dict):
                 continue
-            source_url = source.get('file')
-            if not source_url or not isinstance(source_url, compat_str):
+            source_url = url_or_none(source.get('file'))
+            if not source_url:
                 continue
             ext = determine_ext(source_url)
             if ext == 'm3u8':

youtube_dl/extractor/aparat.py

@@ -5,6 +5,7 @@
 from ..utils import (
     int_or_none,
     mimetype2ext,
+    url_or_none,
 )
 
 
@@ -43,7 +44,7 @@ def _real_extract(self, url):
 
         formats = []
         for item in file_list[0]:
-            file_url = item.get('file')
+            file_url = url_or_none(item.get('file'))
             if not file_url:
                 continue
             ext = mimetype2ext(item.get('type'))

youtube_dl/extractor/ard.py

@@ -5,7 +5,6 @@
 
 from .common import InfoExtractor
 from .generic import GenericIE
-from ..compat import compat_str
 from ..utils import (
     determine_ext,
     ExtractorError,
@@ -15,6 +14,7 @@
     unified_strdate,
     xpath_text,
     update_url_query,
+    url_or_none,
 )
 from ..compat import compat_etree_fromstring
 
@@ -100,7 +100,7 @@ def _extract_formats(self, media_info, video_id):
                 quality = stream.get('_quality')
                 server = stream.get('_server')
                 for stream_url in stream_urls:
-                    if not isinstance(stream_url, compat_str) or '//' not in stream_url:
+                    if not url_or_none(stream_url):
                         continue
                     ext = determine_ext(stream_url)
                     if quality != 'auto' and ext in ('f4m', 'm3u8'):

youtube_dl/extractor/bandcamp.py

@@ -19,6 +19,7 @@
     unescapeHTML,
     update_url_query,
     unified_strdate,
+    url_or_none,
 )
 
 
@@ -131,8 +132,8 @@ def _real_extract(self, url):
                 fatal=False)
             if not stat:
                 continue
-            retry_url = stat.get('retry_url')
-            if not isinstance(retry_url, compat_str):
+            retry_url = url_or_none(stat.get('retry_url'))
+            if not retry_url:
                 continue
             formats.append({
                 'url': self._proto_relative_url(retry_url, 'http:'),
@@ -306,7 +307,7 @@ def _real_extract(self, url):
 
         formats = []
         for format_id, format_url in show['audio_stream'].items():
-            if not isinstance(format_url, compat_str):
+            if not url_or_none(format_url):
                 continue
             for known_ext in KNOWN_EXTENSIONS:
                 if known_ext in format_id:

youtube_dl/extractor/breakcom.py

@@ -4,8 +4,10 @@
 
 from .common import InfoExtractor
 from .youtube import YoutubeIE
-from ..compat import compat_str
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    url_or_none,
+)
 
 
 class BreakIE(InfoExtractor):
@@ -55,8 +57,8 @@ def _real_extract(self, url):
 
         formats = []
         for video in content:
-            video_url = video.get('url')
-            if not video_url or not isinstance(video_url, compat_str):
+            video_url = url_or_none(video.get('url'))
+            if not video_url:
                 continue
             bitrate = int_or_none(self._search_regex(
                 r'(\d+)_kbps', video_url, 'tbr', default=None))

youtube_dl/extractor/cammodels.py

@@ -2,10 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     int_or_none,
+    url_or_none,
 )
 
 
@@ -56,8 +56,8 @@ def _real_extract(self, url):
             for media in encodings:
                 if not isinstance(media, dict):
                     continue
-                media_url = media.get('location')
-                if not media_url or not isinstance(media_url, compat_str):
+                media_url = url_or_none(media.get('location'))
+                if not media_url:
                     continue
 
                 format_id_list = [format_id]

youtube_dl/extractor/ccma.py

@@ -4,13 +4,13 @@
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     clean_html,
     int_or_none,
     parse_duration,
     parse_iso8601,
     parse_resolution,
+    url_or_none,
 )
 
 
@@ -53,8 +53,8 @@ def _real_extract(self, url):
         media_url = media['media']['url']
         if isinstance(media_url, list):
             for format_ in media_url:
-                format_url = format_.get('file')
-                if not format_url or not isinstance(format_url, compat_str):
+                format_url = url_or_none(format_.get('file'))
+                if not format_url:
                     continue
                 label = format_.get('label')
                 f = parse_resolution(label)

youtube_dl/extractor/crackle.py

@@ -4,16 +4,14 @@
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_str,
-    compat_HTTPError,
-)
+from ..compat import compat_HTTPError
 from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
     parse_age_limit,
     parse_duration,
+    url_or_none,
     ExtractorError
 )
 
@@ -86,8 +84,8 @@ def _real_extract(self, url):
             for e in media['MediaURLs']:
                 if e.get('UseDRM') is True:
                     continue
-                format_url = e.get('Path')
-                if not format_url or not isinstance(format_url, compat_str):
+                format_url = url_or_none(e.get('Path'))
+                if not format_url:
                     continue
                 ext = determine_ext(format_url)
                 if ext == 'm3u8':
@@ -124,8 +122,8 @@ def _real_extract(self, url):
                 for cc_file in cc_files:
                     if not isinstance(cc_file, dict):
                         continue
-                    cc_url = cc_file.get('Path')
-                    if not cc_url or not isinstance(cc_url, compat_str):
+                    cc_url = url_or_none(cc_file.get('Path'))
+                    if not cc_url:
                         continue
                     lang = cc_file.get('Locale') or 'en'
                     subtitles.setdefault(lang, []).append({'url': cc_url})

youtube_dl/extractor/dctp.py

@@ -7,6 +7,7 @@
     float_or_none,
     int_or_none,
     unified_timestamp,
+    url_or_none,
 )
 
 
@@ -69,7 +70,7 @@ def _real_extract(self, url):
             endpoint = next(
                 server['endpoint']
                 for server in servers
-                if isinstance(server.get('endpoint'), compat_str) and
+                if url_or_none(server.get('endpoint')) and
                 'cloudfront' in server['endpoint'])
         else:
             endpoint = 'rtmpe://s2pqqn4u96e4j8.cloudfront.net/cfx/st/'
@@ -92,8 +93,8 @@ def _real_extract(self, url):
             for image in images:
                 if not isinstance(image, dict):
                     continue
-                image_url = image.get('url')
-                if not image_url or not isinstance(image_url, compat_str):
+                image_url = url_or_none(image.get('url'))
+                if not image_url:
                     continue
                 thumbnails.append({
                     'url': image_url,

youtube_dl/extractor/discoverygo.py

@@ -3,7 +3,6 @@
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     determine_ext,
     extract_attributes,
@@ -12,6 +11,7 @@
     parse_age_limit,
     remove_end,
     unescapeHTML,
+    url_or_none,
 )
 
 
@@ -69,9 +69,8 @@ def _extract_video_info(self, video, stream, display_id):
         captions = stream.get('captions')
         if isinstance(captions, list):
             for caption in captions:
-                subtitle_url = caption.get('fileUrl')
-                if (not subtitle_url or not isinstance(subtitle_url, compat_str) or
-                        not subtitle_url.startswith('http')):
+                subtitle_url = url_or_none(caption.get('fileUrl'))
+                if not subtitle_url or not subtitle_url.startswith('http'):
                     continue
                 lang = caption.get('fileLang', 'en')
                 ext = determine_ext(subtitle_url)