Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-05 18:52:48 +01:00
Code Issues Releases Activity

a number of new tests and fixes; all tests green on 3.3

Browse Source
This commit is contained in:
Filippo Valsorda 2012-12-17 18:33:11 +01:00
parent f7b111b7d1
commit 937021133f
2 changed files with 44 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
test/tests.json
View File

@ -70,5 +70,22 @@
"url": "http://www.twitch.tv/thegamedevhub/b/296128360", "url": "http://www.twitch.tv/thegamedevhub/b/296128360",
"file": "296128360.flv", "file": "296128360.flv",
"md5": "ecaa8a790c22a40770901460af191c9a" "md5": "ecaa8a790c22a40770901460af191c9a"
},
{
"name": "MyVideo",
"url": "http://www.myvideo.de/watch/8229274/bowling_fail_or_win",
"file": "8229274.flv",
"md5": "2d2753e8130479ba2cb7e0a37002053e"
},
{
"name": "Escapist",
"url": "http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate",
"file": "6618-Breaking-Down-Baldurs-Gate.flv",
"md5": "c6793dbda81388f4264c1ba18684a74d"
},
{
"name": "GooglePlus",
"url": "https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH",
"file": "ZButuJc6CtH.flv"
} }
] ]

44
youtube_dl/InfoExtractors.py
View File

@ -799,6 +799,7 @@ def _real_extract(self, url):
class YahooIE(InfoExtractor): class YahooIE(InfoExtractor):
"""Information extractor for video.yahoo.com.""" """Information extractor for video.yahoo.com."""
_WORKING = False
# _VALID_URL matches all Yahoo! Video URLs # _VALID_URL matches all Yahoo! Video URLs
# _VPAGE_URL matches only the extractable '/watch/' URLs # _VPAGE_URL matches only the extractable '/watch/' URLs
_VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
@ -1170,7 +1171,7 @@ def extractPlus7Stream(self, url):
'url': compat_urllib_parse.unquote(info.get('url')), 'url': compat_urllib_parse.unquote(info.get('url')),
'uploader': u'arte.tv', 'uploader': u'arte.tv',
'upload_date': info.get('date'), 'upload_date': info.get('date'),
'title': info.get('title'), 'title': info.get('title').decode('utf-8'),
'ext': u'mp4', 'ext': u'mp4',
'format': u'NA', 'format': u'NA',
'player_url': None, 'player_url': None,
@ -1495,6 +1496,8 @@ def _download_n_results(self, query, n):
class YahooSearchIE(InfoExtractor): class YahooSearchIE(InfoExtractor):
"""Information Extractor for Yahoo! Video search queries.""" """Information Extractor for Yahoo! Video search queries."""
_WORKING = False
_VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+' _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
_TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
_VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
@ -2274,7 +2277,7 @@ def _real_extract(self,url):
request = compat_urllib_request.Request('http://www.myvideo.de/watch/%s' % video_id) request = compat_urllib_request.Request('http://www.myvideo.de/watch/%s' % video_id)
try: try:
self.report_download_webpage(video_id) self.report_download_webpage(video_id)
webpage = compat_urllib_request.urlopen(request).read() webpage = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
return return
@ -2556,7 +2559,9 @@ def _real_extract(self, url):
self.report_config_download(showName) self.report_config_download(showName)
try: try:
configJSON = compat_urllib_request.urlopen(configUrl).read() configJSON = compat_urllib_request.urlopen(configUrl)
m = re.match(r'text/html; charset="?([^"]+)"?', configJSON.headers['Content-Type'])
configJSON = configJSON.read().decode(m.group(1) if m else 'utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable to download configuration: ' + compat_str(err)) self._downloader.trouble(u'ERROR: unable to download configuration: ' + compat_str(err))
return return
@ -2876,6 +2881,8 @@ def _real_extract(self, url):
class MixcloudIE(InfoExtractor): class MixcloudIE(InfoExtractor):
"""Information extractor for www.mixcloud.com""" """Information extractor for www.mixcloud.com"""
_WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/
_VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
IE_NAME = u'mixcloud' IE_NAME = u'mixcloud'
@ -3378,7 +3385,7 @@ def _real_extract(self, url):
class GooglePlusIE(InfoExtractor): class GooglePlusIE(InfoExtractor):
"""Information extractor for plus.google.com.""" """Information extractor for plus.google.com."""
_VALID_URL = r'(?:https://)?plus\.google\.com/(?:\w+/)*?(\d+)/posts/(\w+)' _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
IE_NAME = u'plus.google' IE_NAME = u'plus.google'
def __init__(self, downloader=None): def __init__(self, downloader=None):
@ -3386,7 +3393,7 @@ def __init__(self, downloader=None):
def report_extract_entry(self, url): def report_extract_entry(self, url):
"""Report downloading extry""" """Report downloading extry"""
self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url.decode('utf-8')) self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url)
def report_date(self, upload_date): def report_date(self, upload_date):
"""Report downloading extry""" """Report downloading extry"""
@ -3394,15 +3401,15 @@ def report_date(self, upload_date):
def report_uploader(self, uploader): def report_uploader(self, uploader):
"""Report downloading extry""" """Report downloading extry"""
self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader.decode('utf-8')) self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader)
def report_title(self, video_title): def report_title(self, video_title):
"""Report downloading extry""" """Report downloading extry"""
self._downloader.to_screen(u'[plus.google] Title: %s' % video_title.decode('utf-8')) self._downloader.to_screen(u'[plus.google] Title: %s' % video_title)
def report_extract_vid_page(self, video_page): def report_extract_vid_page(self, video_page):
"""Report information extraction.""" """Report information extraction."""
self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page.decode('utf-8')) self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page)
def _real_extract(self, url): def _real_extract(self, url):
# Extract id from URL # Extract id from URL
@ -3412,7 +3419,7 @@ def _real_extract(self, url):
return return
post_url = mobj.group(0) post_url = mobj.group(0)
video_id = mobj.group(2) video_id = mobj.group(1)
video_extension = 'flv' video_extension = 'flv'
@ -3420,7 +3427,7 @@ def _real_extract(self, url):
self.report_extract_entry(post_url) self.report_extract_entry(post_url)
request = compat_urllib_request.Request(post_url) request = compat_urllib_request.Request(post_url)
try: try:
webpage = compat_urllib_request.urlopen(request).read() webpage = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % compat_str(err))
return return
@ -3462,7 +3469,7 @@ def _real_extract(self, url):
video_page = mobj.group(1) video_page = mobj.group(1)
request = compat_urllib_request.Request(video_page) request = compat_urllib_request.Request(video_page)
try: try:
webpage = compat_urllib_request.urlopen(request).read() webpage = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
return return
@ -3484,16 +3491,19 @@ def _real_extract(self, url):
# Only get the url. The resolution part in the tuple has no use anymore # Only get the url. The resolution part in the tuple has no use anymore
video_url = video_url[-1] video_url = video_url[-1]
# Treat escaped \u0026 style hex # Treat escaped \u0026 style hex
video_url = unicode(video_url, "unicode_escape") try:
video_url = video_url.decode("unicode_escape")
except AttributeError: # Python 3
video_url = bytes(video_url, 'ascii').decode('unicode-escape')
return [{ return [{
'id': video_id.decode('utf-8'), 'id': video_id,
'url': video_url, 'url': video_url,
'uploader': uploader.decode('utf-8'), 'uploader': uploader,
'upload_date': upload_date.decode('utf-8'), 'upload_date': upload_date,
'title': video_title.decode('utf-8'), 'title': video_title,
'ext': video_extension.decode('utf-8'), 'ext': video_extension,
}] }]
class NBAIE(InfoExtractor): class NBAIE(InfoExtractor):