|
|
@ -47,6 +47,7 @@ std_headers = { |
|
|
|
|
|
|
|
simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') |
|
|
|
|
|
|
|
|
|
|
|
def preferredencoding(): |
|
|
|
"""Get preferred encoding. |
|
|
|
|
|
|
@ -63,6 +64,7 @@ def preferredencoding(): |
|
|
|
yield pref |
|
|
|
return yield_preferredencoding().next() |
|
|
|
|
|
|
|
|
|
|
|
def htmlentity_transform(matchobj): |
|
|
|
"""Transforms an HTML entity to a Unicode character. |
|
|
|
|
|
|
@ -89,11 +91,13 @@ 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. |
|
|
|
|
|
|
@ -120,13 +124,15 @@ 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 |
|
|
|
timetuple = email.utils.parsedate_tz(timestr) |
|
|
|
if timetuple is not None: |
|
|
|
timestamp = email.utils.mktime_tz(timetuple) |
|
|
|
return timestamp |
|
|
|
"""Convert RFC 2822 defined time string into system timestamp""" |
|
|
|
timestamp = None |
|
|
|
timetuple = email.utils.parsedate_tz(timestr) |
|
|
|
if timetuple is not None: |
|
|
|
timestamp = email.utils.mktime_tz(timetuple) |
|
|
|
return timestamp |
|
|
|
|
|
|
|
|
|
|
|
class DownloadError(Exception): |
|
|
|
"""Download Error exception. |
|
|
@ -137,6 +143,7 @@ class DownloadError(Exception): |
|
|
|
""" |
|
|
|
pass |
|
|
|
|
|
|
|
|
|
|
|
class SameFileError(Exception): |
|
|
|
"""Same File exception. |
|
|
|
|
|
|
@ -145,6 +152,7 @@ class SameFileError(Exception): |
|
|
|
""" |
|
|
|
pass |
|
|
|
|
|
|
|
|
|
|
|
class PostProcessingError(Exception): |
|
|
|
"""Post Processing exception. |
|
|
|
|
|
|
@ -153,6 +161,7 @@ class PostProcessingError(Exception): |
|
|
|
""" |
|
|
|
pass |
|
|
|
|
|
|
|
|
|
|
|
class UnavailableVideoError(Exception): |
|
|
|
"""Unavailable Format exception. |
|
|
|
|
|
|
@ -161,6 +170,7 @@ class UnavailableVideoError(Exception): |
|
|
|
""" |
|
|
|
pass |
|
|
|
|
|
|
|
|
|
|
|
class ContentTooShortError(Exception): |
|
|
|
"""Content Too Short exception. |
|
|
|
|
|
|
@ -176,6 +186,7 @@ class ContentTooShortError(Exception): |
|
|
|
self.downloaded = downloaded |
|
|
|
self.expected = expected |
|
|
|
|
|
|
|
|
|
|
|
class YoutubeDLHandler(urllib2.HTTPHandler): |
|
|
|
"""Handler for HTTP requests and responses. |
|
|
|
|
|
|
@ -185,11 +196,11 @@ class YoutubeDLHandler(urllib2.HTTPHandler): |
|
|
|
a particular request, the original request in the program code only has |
|
|
|
to include the HTTP header "Youtubedl-No-Compression", which will be |
|
|
|
removed before making the real request. |
|
|
|
|
|
|
|
|
|
|
|
Part of this code was copied from: |
|
|
|
|
|
|
|
http://techknack.net/python-urllib2-handlers/ |
|
|
|
|
|
|
|
http://techknack.net/python-urllib2-handlers/ |
|
|
|
|
|
|
|
Andrew Rowls, the author of that code, agreed to release it to the |
|
|
|
public domain. |
|
|
|
""" |
|
|
@ -200,7 +211,7 @@ class YoutubeDLHandler(urllib2.HTTPHandler): |
|
|
|
return zlib.decompress(data, -zlib.MAX_WBITS) |
|
|
|
except zlib.error: |
|
|
|
return zlib.decompress(data) |
|
|
|
|
|
|
|
|
|
|
|
@staticmethod |
|
|
|
def addinfourl_wrapper(stream, headers, url, code): |
|
|
|
if hasattr(urllib2.addinfourl, 'getcode'): |
|
|
@ -208,7 +219,7 @@ class YoutubeDLHandler(urllib2.HTTPHandler): |
|
|
|
ret = urllib2.addinfourl(stream, headers, url) |
|
|
|
ret.code = code |
|
|
|
return ret |
|
|
|
|
|
|
|
|
|
|
|
def http_request(self, req): |
|
|
|
for h in std_headers: |
|
|
|
if h in req.headers: |
|
|
@ -234,6 +245,7 @@ class YoutubeDLHandler(urllib2.HTTPHandler): |
|
|
|
resp.msg = old_resp.msg |
|
|
|
return resp |
|
|
|
|
|
|
|
|
|
|
|
class FileDownloader(object): |
|
|
|
"""File Downloader class. |
|
|
|
|
|
|
@ -325,7 +337,7 @@ class FileDownloader(object): |
|
|
|
else: |
|
|
|
exponent = long(math.log(bytes, 1024.0)) |
|
|
|
suffix = 'bkMGTPEZY'[exponent] |
|
|
|
converted = float(bytes) / float(1024**exponent) |
|
|
|
converted = float(bytes) / float(1024 ** exponent) |
|
|
|
return '%.2f%s' % (converted, suffix) |
|
|
|
|
|
|
|
@staticmethod |
|
|
@ -463,7 +475,7 @@ class FileDownloader(object): |
|
|
|
os.rename(old_filename, new_filename) |
|
|
|
except (IOError, OSError), err: |
|
|
|
self.trouble(u'ERROR: unable to rename file') |
|
|
|
|
|
|
|
|
|
|
|
def try_utime(self, filename, last_modified_hdr): |
|
|
|
"""Try to set the last-modified time of the given file.""" |
|
|
|
if last_modified_hdr is None: |
|
|
@ -477,7 +489,7 @@ class FileDownloader(object): |
|
|
|
if filetime is None: |
|
|
|
return |
|
|
|
try: |
|
|
|
os.utime(filename,(time.time(), filetime)) |
|
|
|
os.utime(filename, (time.time(), filetime)) |
|
|
|
except: |
|
|
|
pass |
|
|
|
|
|
|
@ -680,7 +692,7 @@ class FileDownloader(object): |
|
|
|
# Request parameters in case of being able to resume |
|
|
|
if self.params.get('continuedl', False) and resume_len != 0: |
|
|
|
self.report_resuming_byte(resume_len) |
|
|
|
request.add_header('Range','bytes=%d-' % resume_len) |
|
|
|
request.add_header('Range', 'bytes=%d-' % resume_len) |
|
|
|
open_mode = 'ab' |
|
|
|
|
|
|
|
count = 0 |
|
|
@ -706,7 +718,7 @@ class FileDownloader(object): |
|
|
|
else: |
|
|
|
# Examine the reported length |
|
|
|
if (content_length is not None and |
|
|
|
(resume_len - 100 < long(content_length) < resume_len + 100)): |
|
|
|
(resume_len - 100 < long(content_length) < resume_len + 100)): |
|
|
|
# The file had already been fully downloaded. |
|
|
|
# Explanation to the above condition: in issue #175 it was revealed that |
|
|
|
# YouTube sometimes adds or removes a few bytes from the end of the file, |
|
|
@ -784,6 +796,7 @@ class FileDownloader(object): |
|
|
|
|
|
|
|
return True |
|
|
|
|
|
|
|
|
|
|
|
class InfoExtractor(object): |
|
|
|
"""Information Extractor class. |
|
|
|
|
|
|
@ -855,6 +868,7 @@ class InfoExtractor(object): |
|
|
|
"""Real extraction process. Redefine in subclasses.""" |
|
|
|
pass |
|
|
|
|
|
|
|
|
|
|
|
class YoutubeIE(InfoExtractor): |
|
|
|
"""Information extractor for youtube.com.""" |
|
|
|
|
|
|
@ -1009,7 +1023,7 @@ class YoutubeIE(InfoExtractor): |
|
|
|
self.report_video_info_webpage_download(video_id) |
|
|
|
for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: |
|
|
|
video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' |
|
|
|
% (video_id, el_type)) |
|
|
|
% (video_id, el_type)) |
|
|
|
request = urllib2.Request(video_info_url) |
|
|
|
try: |
|
|
|
video_info_webpage = urllib2.urlopen(request).read() |
|
|
@ -1371,6 +1385,7 @@ class DailymotionIE(InfoExtractor): |
|
|
|
except UnavailableVideoError: |
|
|
|
self._downloader.trouble(u'\nERROR: unable to download video') |
|
|
|
|
|
|
|
|
|
|
|
class GoogleIE(InfoExtractor): |
|
|
|
"""Information extractor for video.google.com.""" |
|
|
|
|
|
|
@ -1464,7 +1479,6 @@ class GoogleIE(InfoExtractor): |
|
|
|
else: # we need something to pass to process_info |
|
|
|
video_thumbnail = '' |
|
|
|
|
|
|
|
|
|
|
|
try: |
|
|
|
# Process video information |
|
|
|
self._downloader.process_info({ |
|
|
@ -1664,7 +1678,8 @@ 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) |
|
|
@ -1685,8 +1700,8 @@ class YahooIE(InfoExtractor): |
|
|
|
yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents |
|
|
|
yv_bitrate = '700' # according to Wikipedia this is hard-coded |
|
|
|
request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + |
|
|
|
'&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + |
|
|
|
'&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') |
|
|
|
'&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + |
|
|
|
'&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') |
|
|
|
try: |
|
|
|
self.report_download_webpage(video_id) |
|
|
|
webpage = urllib2.urlopen(request).read() |
|
|
@ -1779,11 +1794,11 @@ class GenericIE(InfoExtractor): |
|
|
|
return |
|
|
|
|
|
|
|
video_url = urllib.unquote(mobj.group(1)) |
|
|
|
video_id = os.path.basename(video_url) |
|
|
|
video_id = os.path.basename(video_url) |
|
|
|
|
|
|
|
# here's a fun little line of code for you: |
|
|
|
video_extension = os.path.splitext(video_id)[1][1:] |
|
|
|
video_id = os.path.splitext(video_id)[0] |
|
|
|
video_id = os.path.splitext(video_id)[0] |
|
|
|
|
|
|
|
# it's tempting to parse this further, but you would |
|
|
|
# have to take into account all the variations like |
|
|
@ -1856,7 +1871,7 @@ class YoutubeSearchIE(InfoExtractor): |
|
|
|
|
|
|
|
prefix, query = query.split(':') |
|
|
|
prefix = prefix[8:] |
|
|
|
query = query.encode('utf-8') |
|
|
|
query = query.encode('utf-8') |
|
|
|
if prefix == '': |
|
|
|
self._download_n_results(query, 1) |
|
|
|
return |
|
|
@ -1870,7 +1885,7 @@ class YoutubeSearchIE(InfoExtractor): |
|
|
|
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) |
|
|
|
return |
|
|
|
elif n > self._max_youtube_results: |
|
|
|
self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) |
|
|
|
self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) |
|
|
|
n = self._max_youtube_results |
|
|
|
self._download_n_results(query, n) |
|
|
|
return |
|
|
@ -1914,6 +1929,7 @@ class YoutubeSearchIE(InfoExtractor): |
|
|
|
|
|
|
|
pagenum = pagenum + 1 |
|
|
|
|
|
|
|
|
|
|
|
class GoogleSearchIE(InfoExtractor): |
|
|
|
"""Information Extractor for Google Video search queries.""" |
|
|
|
_VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+' |
|
|
@ -1947,7 +1963,7 @@ class GoogleSearchIE(InfoExtractor): |
|
|
|
|
|
|
|
prefix, query = query.split(':') |
|
|
|
prefix = prefix[8:] |
|
|
|
query = query.encode('utf-8') |
|
|
|
query = query.encode('utf-8') |
|
|
|
if prefix == '': |
|
|
|
self._download_n_results(query, 1) |
|
|
|
return |
|
|
@ -1961,7 +1977,7 @@ class GoogleSearchIE(InfoExtractor): |
|
|
|
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) |
|
|
|
return |
|
|
|
elif n > self._max_google_results: |
|
|
|
self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) |
|
|
|
self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) |
|
|
|
n = self._max_google_results |
|
|
|
self._download_n_results(query, n) |
|
|
|
return |
|
|
@ -2005,6 +2021,7 @@ class GoogleSearchIE(InfoExtractor): |
|
|
|
|
|
|
|
pagenum = pagenum + 1 |
|
|
|
|
|
|
|
|
|
|
|
class YahooSearchIE(InfoExtractor): |
|
|
|
"""Information Extractor for Yahoo! Video search queries.""" |
|
|
|
_VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+' |
|
|
@ -2038,7 +2055,7 @@ class YahooSearchIE(InfoExtractor): |
|
|
|
|
|
|
|
prefix, query = query.split(':') |
|
|
|
prefix = prefix[8:] |
|
|
|
query = query.encode('utf-8') |
|
|
|
query = query.encode('utf-8') |
|
|
|
if prefix == '': |
|
|
|
self._download_n_results(query, 1) |
|
|
|
return |
|
|
@ -2052,7 +2069,7 @@ class YahooSearchIE(InfoExtractor): |
|
|
|
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) |
|
|
|
return |
|
|
|
elif n > self._max_yahoo_results: |
|
|
|
self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) |
|
|
|
self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) |
|
|
|
n = self._max_yahoo_results |
|
|
|
self._download_n_results(query, n) |
|
|
|
return |
|
|
@ -2096,6 +2113,7 @@ class YahooSearchIE(InfoExtractor): |
|
|
|
|
|
|
|
pagenum = pagenum + 1 |
|
|
|
|
|
|
|
|
|
|
|
class YoutubePlaylistIE(InfoExtractor): |
|
|
|
"""Information Extractor for YouTube playlists.""" |
|
|
|
|
|
|
@ -2172,6 +2190,7 @@ class YoutubePlaylistIE(InfoExtractor): |
|
|
|
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) |
|
|
|
return |
|
|
|
|
|
|
|
|
|
|
|
class YoutubeUserIE(InfoExtractor): |
|
|
|
"""Information Extractor for YouTube users.""" |
|
|
|
|
|
|
@ -2193,7 +2212,7 @@ class YoutubeUserIE(InfoExtractor): |
|
|
|
def report_download_page(self, username, start_index): |
|
|
|
"""Report attempt to download user page.""" |
|
|
|
self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' % |
|
|
|
(username, start_index, start_index + self._GDATA_PAGE_SIZE)) |
|
|
|
(username, start_index, start_index + self._GDATA_PAGE_SIZE)) |
|
|
|
|
|
|
|
def _real_initialize(self): |
|
|
|
self._youtube_ie.initialize() |
|
|
@ -2255,9 +2274,9 @@ class YoutubeUserIE(InfoExtractor): |
|
|
|
video_ids = video_ids[playliststart:] |
|
|
|
else: |
|
|
|
video_ids = video_ids[playliststart:playlistend] |
|
|
|
|
|
|
|
|
|
|
|
self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" % |
|
|
|
(username, all_ids_count, len(video_ids))) |
|
|
|
(username, all_ids_count, len(video_ids))) |
|
|
|
|
|
|
|
for video_id in video_ids: |
|
|
|
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id) |
|
|
@ -2342,6 +2361,7 @@ class DepositFilesIE(InfoExtractor): |
|
|
|
except UnavailableVideoError, err: |
|
|
|
self._downloader.trouble(u'ERROR: unable to download file') |
|
|
|
|
|
|
|
|
|
|
|
class FacebookIE(InfoExtractor): |
|
|
|
"""Information Extractor for Facebook""" |
|
|
|
|
|
|
@ -2510,7 +2530,7 @@ class FacebookIE(InfoExtractor): |
|
|
|
# description |
|
|
|
video_description = 'No description available.' |
|
|
|
if (self._downloader.params.get('forcedescription', False) and |
|
|
|
'description' in video_info): |
|
|
|
'description' in video_info): |
|
|
|
video_description = video_info['description'] |
|
|
|
|
|
|
|
url_map = video_info['video_urls'] |
|
|
@ -2565,6 +2585,7 @@ class FacebookIE(InfoExtractor): |
|
|
|
except UnavailableVideoError, err: |
|
|
|
self._downloader.trouble(u'\nERROR: unable to download video') |
|
|
|
|
|
|
|
|
|
|
|
class PostProcessor(object): |
|
|
|
"""Post Processor class. |
|
|
|
|
|
|
@ -2611,6 +2632,7 @@ class PostProcessor(object): |
|
|
|
""" |
|
|
|
return information # by default, do nothing |
|
|
|
|
|
|
|
|
|
|
|
class FFmpegExtractAudioPP(PostProcessor): |
|
|
|
|
|
|
|
def __init__(self, downloader=None, preferredcodec=None): |
|
|
|