|
|
|
@ -133,7 +133,9 @@ class SubstackIE(InfoExtractor):
|
|
|
|
|
canonical_url = urllib.parse.urlparse(url)._replace(netloc=domain).geturl()
|
|
|
|
|
|
|
|
|
|
post_type = webpage_info['post']['type']
|
|
|
|
|
post_title = traverse_obj(webpage_info, ('post', 'title'))
|
|
|
|
|
formats, subtitles = [], {}
|
|
|
|
|
all_results = []
|
|
|
|
|
result_info = {
|
|
|
|
|
'id': str(webpage_info['post']['id']),
|
|
|
|
|
'subtitles': subtitles,
|
|
|
|
@ -144,7 +146,9 @@ class SubstackIE(InfoExtractor):
|
|
|
|
|
'uploader_id': str_or_none(traverse_obj(webpage_info, ('post', 'publication_id'))),
|
|
|
|
|
'webpage_url': canonical_url,
|
|
|
|
|
}
|
|
|
|
|
# handle specific post types which are based on media
|
|
|
|
|
if post_type == 'podcast':
|
|
|
|
|
podcast_result = dict(result_info)
|
|
|
|
|
fmt = {'url': webpage_info['post']['podcast_url']}
|
|
|
|
|
if not determine_ext(fmt['url'], default_ext=None):
|
|
|
|
|
# The redirected format URL expires but the original URL doesn't,
|
|
|
|
@ -153,21 +157,21 @@ class SubstackIE(InfoExtractor):
|
|
|
|
|
HEADRequest(fmt['url']), display_id,
|
|
|
|
|
'Resolving podcast file extension',
|
|
|
|
|
'Podcast URL is invalid').url)
|
|
|
|
|
result_info['formats'] = [fmt]
|
|
|
|
|
return result_info
|
|
|
|
|
elif post_type == 'video':
|
|
|
|
|
podcast_result['formats'] = [fmt]
|
|
|
|
|
all_results.append(podcast_result)
|
|
|
|
|
if post_type == 'video':
|
|
|
|
|
video_result = dict(result_info)
|
|
|
|
|
formats, subtitles = self._extract_video_formats(
|
|
|
|
|
webpage_info['post']['videoUpload']['id'], canonical_url)
|
|
|
|
|
result_info.update({
|
|
|
|
|
video_result.update({
|
|
|
|
|
'formats': formats,
|
|
|
|
|
'subtitles': subtitles,
|
|
|
|
|
})
|
|
|
|
|
return result_info
|
|
|
|
|
elif post_type == 'newsletter':
|
|
|
|
|
results = []
|
|
|
|
|
all_results.append(video_result)
|
|
|
|
|
|
|
|
|
|
# search for embedded players on the page
|
|
|
|
|
found_items = []
|
|
|
|
|
post_id = str(webpage_info['post']['id'])
|
|
|
|
|
post_title = traverse_obj(webpage_info, ('post', 'title'))
|
|
|
|
|
assert result_info['uploader_id'] is not None, 'newsletter posted without user_id'
|
|
|
|
|
|
|
|
|
|
video_players = re.finditer(
|
|
|
|
@ -230,12 +234,10 @@ class SubstackIE(InfoExtractor):
|
|
|
|
|
'uploader_id': str_or_none(json_vid_data.get('user_id', None)),
|
|
|
|
|
'uploader': None, # video uploader username is not included
|
|
|
|
|
})
|
|
|
|
|
results.append(new_result)
|
|
|
|
|
all_results.append(new_result)
|
|
|
|
|
|
|
|
|
|
if len(results) > 0:
|
|
|
|
|
if len(all_results) > 0:
|
|
|
|
|
playlist_title = f'Videos for {post_title}'
|
|
|
|
|
return self.playlist_result(results, post_id, playlist_title)
|
|
|
|
|
return self.playlist_result(all_results, post_id, playlist_title)
|
|
|
|
|
else:
|
|
|
|
|
self.raise_no_formats(f'Page type "{post_type}" contains no supported embeds')
|
|
|
|
|
|
|
|
|
|
self.raise_no_formats(f'Page type "{post_type}" is not supported')
|
|
|
|
|