github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-04 14:43:35 -05:00
Code Issues Projects Releases Packages Wiki Activity

[extractor/detik] Avoid unnecessary extraction

Browse source
This commit is contained in:
pukkandan 2022-10-04 10:31:49 +05:30
parent 57fb88093e
commit 1305b659ef
No known key found for this signature in database
GPG key ID: 7EEE9E1E817D0A39
1 changed files with 4 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
yt_dlp/extractor/detik.py
View file

@ -114,18 +114,15 @@ class DetikEmbedIE(InfoExtractor):
}] }]
def _extract_from_webpage(self, url, webpage): def _extract_from_webpage(self, url, webpage):
display_id = url_basename(url)
player_type, video_data = self._search_regex( player_type, video_data = self._search_regex(
r'<script\s*[^>]+src="https?://(aws)?cdn\.detik\.net\.id/(?P<type>flowplayer|detikVideo)[^>]+>\s*(?P<video_data>{[^}]+})', r'<script\s*[^>]+src="https?://(aws)?cdn\.detik\.net\.id/(?P<type>flowplayer|detikVideo)[^>]+>\s*(?P<video_data>{[^}]+})',
webpage, 'playerjs', group=('type', 'video_data'), default=(None, '')) webpage, 'playerjs', group=('type', 'video_data'), default=(None, ''))
json_ld_data = self._search_json_ld(webpage, display_id, default={})
extra_info_dict = {}
if not player_type: if not player_type:
return return
elif player_type == 'flowplayer': display_id, extra_info_dict = url_basename(url), {}
if player_type == 'flowplayer':
video_json_data = self._parse_json(video_data.replace('\'', '"'), display_id) video_json_data = self._parse_json(video_data.replace('\'', '"'), display_id)
video_url = video_json_data['videoUrl'] video_url = video_json_data['videoUrl']
@ -151,6 +148,7 @@ def _extract_from_webpage(self, url, webpage):
formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_url, display_id) formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_url, display_id)
self._sort_formats(formats) self._sort_formats(formats)
json_ld_data = self._search_json_ld(webpage, display_id, default={})
yield merge_dicts(json_ld_data, extra_info_dict, { yield merge_dicts(json_ld_data, extra_info_dict, {
'display_id': display_id, 'display_id': display_id,
'title': self._html_search_meta(['og:title', 'originalTitle'], webpage) or self._html_extract_title(webpage), 'title': self._html_search_meta(['og:title', 'originalTitle'], webpage) or self._html_extract_title(webpage),