X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9d6a3ba754469c85b7f0f88714203f99ac69087a..5920ef2b4969021b7f83d154b325036d9b598877:/youtube_dl/extractor/udemy.py diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index a719699..105826e 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -20,6 +20,7 @@ from ..utils import ( sanitized_Request, try_get, unescapeHTML, + url_or_none, urlencode_postdata, ) @@ -121,7 +122,9 @@ class UdemyIE(InfoExtractor): raise ExtractorError(error_str, expected=True) def _download_webpage_handle(self, *args, **kwargs): - kwargs.setdefault('headers', {})['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4' + headers = kwargs.get('headers', {}).copy() + headers['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4' + kwargs['headers'] = headers return super(UdemyIE, self)._download_webpage_handle( *args, **compat_kwargs(kwargs)) @@ -265,8 +268,8 @@ class UdemyIE(InfoExtractor): if not isinstance(source_list, list): return for source in source_list: - video_url = source.get('file') or source.get('src') - if not video_url or not isinstance(video_url, compat_str): + video_url = url_or_none(source.get('file') or source.get('src')) + if not video_url: continue if source.get('type') == 'application/x-mpegURL' or determine_ext(video_url) == 'm3u8': formats.extend(self._extract_m3u8_formats( @@ -293,8 +296,8 @@ class UdemyIE(InfoExtractor): continue if track.get('kind') != 'captions': continue - src = track.get('src') - if not src or not isinstance(src, compat_str): + src = url_or_none(track.get('src')) + if not src: continue lang = track.get('language') or track.get( 'srclang') or track.get('label') @@ -314,8 +317,8 @@ class UdemyIE(InfoExtractor): for cc in captions: if not isinstance(cc, dict): continue - cc_url = cc.get('url') - if not cc_url or not isinstance(cc_url, compat_str): + cc_url = url_or_none(cc.get('url')) + if not cc_url: continue lang = try_get(cc, lambda x: x['locale']['locale'], compat_str) sub_dict = (automatic_captions if cc.get('source') == 'auto'