pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-22 20:20:09 +09:00
Code Issues Projects Releases Wiki Activity

[dvtv] remove unnecessary comments and spaces

Browse Source
This commit is contained in:
Remita Amine 2019-04-06 16:29:30 +01:00
parent b9aad6c427
commit 19591facea
1 changed files with 7 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
youtube_dl/extractor/dvtv.py
View File

@ -19,9 +19,7 @@ from ..utils import (
class DVTVIE(InfoExtractor): class DVTVIE(InfoExtractor):
IE_NAME = 'dvtv' IE_NAME = 'dvtv'
IE_DESC = 'http://video.aktualne.cz/' IE_DESC = 'http://video.aktualne.cz/'
_VALID_URL = r'https?://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})' _VALID_URL = r'https?://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})'
_TESTS = [{ _TESTS = [{
'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/', 'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/',
'md5': '67cb83e4a955d36e1b5d31993134a0c2', 'md5': '67cb83e4a955d36e1b5d31993134a0c2',
@ -36,7 +34,7 @@ class DVTVIE(InfoExtractor):
}, { }, {
'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/', 'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/',
'info_dict': { 'info_dict': {
'title': r're:^DVTV 16\. 12\. 2014: útok Talibanu, boj o kliniku, uprchlíci', 'title': r'DVTV 16. 12. 2014: útok Talibanu, boj o kliniku, uprchlíci',
'id': '973eb3bc854e11e498be002590604f2e', 'id': '973eb3bc854e11e498be002590604f2e',
}, },
'playlist': [{ 'playlist': [{
@ -115,17 +113,14 @@ class DVTVIE(InfoExtractor):
}] }]
def _parse_video_metadata(self, js, video_id, timestamp): def _parse_video_metadata(self, js, video_id, timestamp):
data = self._parse_json(js, video_id, transform_source=js_to_json) data = self._parse_json(js, video_id, transform_source=js_to_json)
title = unescapeHTML(data['title'])
live_starter = try_get(data, lambda x: x['plugins']['liveStarter'], dict) live_starter = try_get(data, lambda x: x['plugins']['liveStarter'], dict)
if live_starter: if live_starter:
data.update(live_starter) data.update(live_starter)
title = unescapeHTML(data['title'])
formats = [] formats = []
for tracks in data.get('tracks', {}).values(): for tracks in data.get('tracks', {}).values():
for video in tracks: for video in tracks:
video_url = video.get('src') video_url = video.get('src')
@ -167,36 +162,23 @@ class DVTVIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
timestamp = parse_iso8601(self._html_search_meta( timestamp = parse_iso8601(self._html_search_meta(
'article:published_time', webpage, 'published time', default=None)) 'article:published_time', webpage, 'published time', default=None))
# playlist items = re.findall(r'(?s)playlist\.push\(({.+?})\);', webpage)
items = re.findall(
r"(?s)playlist\.push\(({.+?})\);",
webpage)
if items: if items:
return { return self.playlist_result(
'_type': 'playlist', [self._parse_video_metadata(i, video_id, timestamp) for i in items],
'id': video_id, video_id, self._html_search_meta('twitter:title', webpage))
'title': self._og_search_title(webpage),
'entries': [self._parse_video_metadata(i, video_id, timestamp) for i in items]
}
# single video
item = self._search_regex( item = self._search_regex(
r'(?s)BBXPlayer.setup\((.+?)\);', r'(?s)BBXPlayer\.setup\((.+?)\);',
webpage, 'video', default=None) webpage, 'video', default=None)
if item: if item:
# remove function calls (ex. htmldeentitize) # remove function calls (ex. htmldeentitize)
# TODO this should be fixed in a general way in the js_to_json # TODO this should be fixed in a general way in the js_to_json
item = re.sub(r'\w+?\((.+)\)', r'\1', item) item = re.sub(r'\w+?\((.+)\)', r'\1', item)
if item:
return self._parse_video_metadata(item, video_id, timestamp) return self._parse_video_metadata(item, video_id, timestamp)
raise ExtractorError('Could not find neither video nor playlist') raise ExtractorError('Could not find neither video nor playlist')