|
|
|
@ -201,6 +201,7 @@ def preferredencoding(): |
|
|
|
|
yield pref |
|
|
|
|
return yield_preferredencoding().next() |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def htmlentity_transform(matchobj): |
|
|
|
|
"""Transforms an HTML entity to a Unicode character. |
|
|
|
|
|
|
|
|
@ -227,11 +228,13 @@ def htmlentity_transform(matchobj): |
|
|
|
|
# Unknown entity in name, return its literal representation |
|
|
|
|
return (u'&%s;' % entity) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def sanitize_title(utitle): |
|
|
|
|
"""Sanitizes a video title so it could be used as part of a filename.""" |
|
|
|
|
utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) |
|
|
|
|
return utitle.replace(unicode(os.sep), u'%') |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def sanitize_open(filename, open_mode): |
|
|
|
|
"""Try to open the given filename, and slightly tweak it if this fails. |
|
|
|
|
|
|
|
|
@ -258,6 +261,7 @@ def sanitize_open(filename, open_mode): |
|
|
|
|
stream = open(filename, open_mode) |
|
|
|
|
return (stream, filename) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def timeconvert(timestr): |
|
|
|
|
"""Convert RFC 2822 defined time string into system timestamp""" |
|
|
|
|
timestamp = None |
|
|
|
@ -266,6 +270,7 @@ def timeconvert(timestr): |
|
|
|
|
timestamp = email.utils.mktime_tz(timetuple) |
|
|
|
|
return timestamp |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class DownloadError(Exception): |
|
|
|
|
"""Download Error exception. |
|
|
|
|
|
|
|
|
@ -275,6 +280,7 @@ class DownloadError(Exception): |
|
|
|
|
""" |
|
|
|
|
pass |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class SameFileError(Exception): |
|
|
|
|
"""Same File exception. |
|
|
|
|
|
|
|
|
@ -283,6 +289,7 @@ class SameFileError(Exception): |
|
|
|
|
""" |
|
|
|
|
pass |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class PostProcessingError(Exception): |
|
|
|
|
"""Post Processing exception. |
|
|
|
|
|
|
|
|
@ -291,6 +298,7 @@ class PostProcessingError(Exception): |
|
|
|
|
""" |
|
|
|
|
pass |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class UnavailableVideoError(Exception): |
|
|
|
|
"""Unavailable Format exception. |
|
|
|
|
|
|
|
|
@ -299,6 +307,7 @@ class UnavailableVideoError(Exception): |
|
|
|
|
""" |
|
|
|
|
pass |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class ContentTooShortError(Exception): |
|
|
|
|
"""Content Too Short exception. |
|
|
|
|
|
|
|
|
@ -314,6 +323,7 @@ class ContentTooShortError(Exception): |
|
|
|
|
self.downloaded = downloaded |
|
|
|
|
self.expected = expected |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class YoutubeDLHandler(urllib2.HTTPHandler): |
|
|
|
|
"""Handler for HTTP requests and responses. |
|
|
|
|
|
|
|
|
@ -372,6 +382,7 @@ class YoutubeDLHandler(urllib2.HTTPHandler): |
|
|
|
|
resp.msg = old_resp.msg |
|
|
|
|
return resp |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class FileDownloader(object): |
|
|
|
|
"""File Downloader class. |
|
|
|
|
|
|
|
|
@ -967,6 +978,7 @@ class FileDownloader(object): |
|
|
|
|
|
|
|
|
|
return True |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class InfoExtractor(object): |
|
|
|
|
"""Information Extractor class. |
|
|
|
|
|
|
|
|
@ -1038,6 +1050,7 @@ class InfoExtractor(object): |
|
|
|
|
"""Real extraction process. Redefine in subclasses.""" |
|
|
|
|
pass |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class YoutubeIE(InfoExtractor): |
|
|
|
|
"""Information extractor for youtube.com.""" |
|
|
|
|
|
|
|
|
@ -1561,6 +1574,7 @@ class DailymotionIE(InfoExtractor): |
|
|
|
|
except UnavailableVideoError: |
|
|
|
|
self._downloader.trouble(u'\nERROR: unable to download video') |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class GoogleIE(InfoExtractor): |
|
|
|
|
"""Information extractor for video.google.com.""" |
|
|
|
|
|
|
|
|
@ -1654,7 +1668,6 @@ class GoogleIE(InfoExtractor): |
|
|
|
|
else: # we need something to pass to process_info |
|
|
|
|
video_thumbnail = '' |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
try: |
|
|
|
|
# Process video information |
|
|
|
|
self._downloader.process_info({ |
|
|
|
@ -1854,7 +1867,8 @@ class YahooIE(InfoExtractor): |
|
|
|
|
self._downloader.trouble(u'ERROR: unable to extract video description') |
|
|
|
|
return |
|
|
|
|
video_description = mobj.group(1).decode('utf-8') |
|
|
|
|
if not video_description: video_description = 'No description available.' |
|
|
|
|
if not video_description: |
|
|
|
|
video_description = 'No description available.' |
|
|
|
|
|
|
|
|
|
# Extract video height and width |
|
|
|
|
mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage) |
|
|
|
@ -2220,6 +2234,7 @@ class YoutubeSearchIE(InfoExtractor): |
|
|
|
|
|
|
|
|
|
pagenum = pagenum + 1 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class GoogleSearchIE(InfoExtractor): |
|
|
|
|
"""Information Extractor for Google Video search queries.""" |
|
|
|
|
_VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+' |
|
|
|
@ -2311,6 +2326,7 @@ class GoogleSearchIE(InfoExtractor): |
|
|
|
|
|
|
|
|
|
pagenum = pagenum + 1 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class YahooSearchIE(InfoExtractor): |
|
|
|
|
"""Information Extractor for Yahoo! Video search queries.""" |
|
|
|
|
_VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+' |
|
|
|
@ -2402,6 +2418,7 @@ class YahooSearchIE(InfoExtractor): |
|
|
|
|
|
|
|
|
|
pagenum = pagenum + 1 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class YoutubePlaylistIE(InfoExtractor): |
|
|
|
|
"""Information Extractor for YouTube playlists.""" |
|
|
|
|
|
|
|
|
@ -2478,6 +2495,7 @@ class YoutubePlaylistIE(InfoExtractor): |
|
|
|
|
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) |
|
|
|
|
return |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class YoutubeUserIE(InfoExtractor): |
|
|
|
|
"""Information Extractor for YouTube users.""" |
|
|
|
|
|
|
|
|
@ -2648,6 +2666,7 @@ class DepositFilesIE(InfoExtractor): |
|
|
|
|
except UnavailableVideoError, err: |
|
|
|
|
self._downloader.trouble(u'ERROR: unable to download file') |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class FacebookIE(InfoExtractor): |
|
|
|
|
"""Information Extractor for Facebook""" |
|
|
|
|
|
|
|
|
@ -2989,6 +3008,7 @@ class PostProcessor(object): |
|
|
|
|
""" |
|
|
|
|
return information # by default, do nothing |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class FFmpegExtractAudioPP(PostProcessor): |
|
|
|
|
|
|
|
|
|
def __init__(self, downloader=None, preferredcodec=None): |
|
|
|
|