mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 18:41:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

[nova] Improve extraction (refs #23690)

Browse source
This commit is contained in:
Sergey M․ 2020-02-15 02:16:26 +07:00
parent b68a6e32fb
commit 06f1de2daf
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 22 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

37
youtube_dl/extractor/nova.py
View file

@ -97,7 +97,7 @@ class NovaIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)' _VALID_URL = r'https?://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)'
_TESTS = [{ _TESTS = [{
'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260', 'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260',
'md5': '1dd7b9d5ea27bc361f110cd855a19bd3', 'md5': '249baab7d0104e186e78b0899c7d5f28',
'info_dict': { 'info_dict': {
'id': '1757139', 'id': '1757139',
'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci', 'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci',
@ -119,7 +119,8 @@ class NovaIE(InfoExtractor):
'params': { 'params': {
# rtmp download # rtmp download
'skip_download': True, 'skip_download': True,
} },
'skip': 'gone',
}, { }, {
# media.cms.nova.cz embed # media.cms.nova.cz embed
'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil', 'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil',
@ -134,6 +135,7 @@ class NovaIE(InfoExtractor):
'skip_download': True, 'skip_download': True,
}, },
'add_ie': [NovaEmbedIE.ie_key()], 'add_ie': [NovaEmbedIE.ie_key()],
'skip': 'CHYBA 404: STRÁNKA NENALEZENA',
}, { }, {
'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html', 'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html',
'only_matching': True, 'only_matching': True,
@ -158,14 +160,29 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
description = clean_html(self._og_search_description(webpage, default=None))
if site == 'novaplus':
upload_date = unified_strdate(self._search_regex(
r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None))
elif site == 'fanda':
upload_date = unified_strdate(self._search_regex(
r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None))
else:
upload_date = None
# novaplus # novaplus
embed_id = self._search_regex( embed_id = self._search_regex(
r'<iframe[^>]+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)', r'<iframe[^>]+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)',
webpage, 'embed url', default=None) webpage, 'embed url', default=None)
if embed_id: if embed_id:
return self.url_result( return {
'https://media.cms.nova.cz/embed/%s' % embed_id, '_type': 'url_transparent',
ie=NovaEmbedIE.ie_key(), video_id=embed_id) 'url': 'https://media.cms.nova.cz/embed/%s' % embed_id,
'ie_key': NovaEmbedIE.ie_key(),
'id': embed_id,
'description': description,
'upload_date': upload_date
}
video_id = self._search_regex( video_id = self._search_regex(
[r"(?:media|video_id)\s*:\s*'(\d+)'", [r"(?:media|video_id)\s*:\s*'(\d+)'",
@ -239,18 +256,8 @@ def _real_extract(self, url):
self._sort_formats(formats) self._sort_formats(formats)
title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage) title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage)
description = clean_html(self._og_search_description(webpage, default=None))
thumbnail = config.get('poster') thumbnail = config.get('poster')
if site == 'novaplus':
upload_date = unified_strdate(self._search_regex(
r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None))
elif site == 'fanda':
upload_date = unified_strdate(self._search_regex(
r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None))
else:
upload_date = None
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,