mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-14 20:33:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

raise exceptions on warnings during tests - and solve a couple of them

Browse source
This commit is contained in:
Filippo Valsorda 2013-06-07 11:19:27 +02:00
parent 476203d025
commit be95cac157
2 changed files with 23 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
test/test_download.py
View file

@ -40,18 +40,12 @@ def _try_rm(filename):
class FileDownloader(youtube_dl.FileDownloader): class FileDownloader(youtube_dl.FileDownloader):
def __init__(self, *args, **kwargs): def __init__(self, *args, **kwargs):
self._to_stderr = self.to_stderr
self.to_stderr = self.to_screen self.to_stderr = self.to_screen
self.processed_info_dicts = [] self.processed_info_dicts = []
return youtube_dl.FileDownloader.__init__(self, *args, **kwargs) return youtube_dl.FileDownloader.__init__(self, *args, **kwargs)
def report_warning(self, message): def report_warning(self, message):
# let warnings pass to output # Don't accept warnings during tests
if sys.stderr.isatty() and os.name != 'nt': raise ExtractorError(message)
_msg_header=u'\033[0;33mWARNING:\033[0m'
else:
_msg_header=u'WARNING:'
warning_message=u'%s %s' % (_msg_header,message)
self._to_stderr(warning_message)
def process_info(self, info_dict): def process_info(self, info_dict):
self.processed_info_dicts.append(info_dict) self.processed_info_dicts.append(info_dict)
return youtube_dl.FileDownloader.process_info(self, info_dict) return youtube_dl.FileDownloader.process_info(self, info_dict)

41
youtube_dl/InfoExtractors.py
View file

@ -3161,7 +3161,7 @@ def _real_extract(self, url):
}] }]
class NBAIE(InfoExtractor): class NBAIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$' _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
IE_NAME = u'nba' IE_NAME = u'nba'
def _real_extract(self, url): def _real_extract(self, url):
@ -3170,8 +3170,6 @@ def _real_extract(self, url):
raise ExtractorError(u'Invalid URL: %s' % url) raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1) video_id = mobj.group(1)
if video_id.endswith('/index.html'):
video_id = video_id[:-len('/index.html')]
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
@ -3181,7 +3179,8 @@ def _real_extract(self, url):
title = self._search_regex(r'<meta property="og:title" content="(.*?)"', title = self._search_regex(r'<meta property="og:title" content="(.*?)"',
webpage, 'title', default=shortened_video_id).replace('NBA.com: ', '') webpage, 'title', default=shortened_video_id).replace('NBA.com: ', '')
uploader_date = self._search_regex(r'<b>Date:</b> (.*?)</div>', webpage, 'upload_date', fatal=False) # It isn't there in the HTML it returns to us
# uploader_date = self._search_regex(r'<b>Date:</b> (.*?)</div>', webpage, 'upload_date', fatal=False)
description = self._search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False) description = self._search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False)
@ -3190,7 +3189,7 @@ def _real_extract(self, url):
'url': video_url, 'url': video_url,
'ext': 'mp4', 'ext': 'mp4',
'title': title, 'title': title,
'uploader_date': uploader_date, # 'uploader_date': uploader_date,
'description': description, 'description': description,
} }
return [info] return [info]
@ -3541,19 +3540,22 @@ def _real_extract(self, url):
req.add_header('Cookie', 'age_verified=1') req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id) webpage = self._download_webpage(req, video_id)
# Get the video title # Get JSON parameters
video_title = self._search_regex(r'<h1.*?>(?P<title>.*)</h1>', json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
webpage, u'title').strip() try:
params = json.loads(json_params)
except:
raise ExtractorError(u'Invalid JSON')
# Get the video date self.report_extraction(video_id)
upload_date = self._search_regex(r'Date:</label>(?P<date>.*) </li>', try:
webpage, u'upload date', fatal=False) video_title = params['title']
if upload_date: upload_date = unified_strdate(upload_date.strip()) upload_date = unified_strdate(params['release_date_f'])
video_description = params['description']
# Get the video uploader video_uploader = params['submitted_by']
video_uploader = self._search_regex(r'Submitted:</label>(?P<uploader>.*)</li>', thumbnail = params['thumbnails'][0]['image']
webpage, u'uploader', fatal=False) except KeyError:
if video_uploader: video_uploader = clean_html(video_uploader.strip()) raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
# Get all of the formats available # Get all of the formats available
DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
@ -3592,9 +3594,8 @@ def _real_extract(self, url):
'title': title, 'title': title,
'ext': extension, 'ext': extension,
'format': format, 'format': format,
'thumbnail': None, 'thumbnail': thumbnail,
'description': None, 'description': video_description
'player_url': None
}) })
if self._downloader.params.get('listformats', None): if self._downloader.params.get('listformats', None):