Compare commits
70 Commits
2011.09.17
...
2011.11.23
Author | SHA1 | Date | |
---|---|---|---|
|
fa2672f9fc | ||
|
28e3614bc0 | ||
|
208e095f72 | ||
|
0ae7abe57c | ||
|
dc0a294a73 | ||
|
468c99257c | ||
|
af8e8d63f9 | ||
|
e092418d8b | ||
|
e33e3045c6 | ||
|
cb6568bf21 | ||
|
235b3ba479 | ||
|
5b3330e0cf | ||
|
aab771fbdf | ||
|
00f95a93f5 | ||
|
1724e7c461 | ||
|
3b98a5ddac | ||
|
8b59cc93d5 | ||
|
c3e4e7c182 | ||
|
38348005b3 | ||
|
208c4b9128 | ||
|
ec574c2c41 | ||
|
871be928a8 | ||
|
b20d4f8626 | ||
|
073d7a5985 | ||
|
40306424b1 | ||
|
ecb3bfe543 | ||
|
abeac45abe | ||
|
0fca93ac60 | ||
|
857e5f329a | ||
|
053419cd24 | ||
|
99e207bab0 | ||
|
0067bbe7a7 | ||
|
45aa690868 | ||
|
beb245e92f | ||
|
c424df0d2f | ||
|
87929e4b35 | ||
|
d76736fc5e | ||
|
0f9b77223e | ||
|
9f47175a40 | ||
|
a1a8713aad | ||
|
6501a06d46 | ||
|
8d89fbae5a | ||
|
7a2cf5455c | ||
|
7125a7ca8b | ||
|
54d47874f7 | ||
|
2761012f69 | ||
|
3de2a1e635 | ||
|
1eff9ac0c5 | ||
|
54f329fe93 | ||
|
9baa2ef53b | ||
|
6bde5972c3 | ||
|
36f6cb369b | ||
|
b845d58b04 | ||
|
efb113c736 | ||
|
3ce59dae88 | ||
|
f0b0caa3fa | ||
|
58384838c3 | ||
|
abb870d1ad | ||
|
daa982bc01 | ||
|
767414a292 | ||
|
7b417b388a | ||
|
44424ceee9 | ||
|
08a5b7f800 | ||
|
1cde6f1d52 | ||
|
2d8acd8039 | ||
|
67035ede49 | ||
|
eb6c37da43 | ||
|
2736595628 | ||
|
7b1a2bbe17 | ||
|
c25303c3d5 |
@@ -1 +1 @@
|
||||
2011.09.17
|
||||
2011.11.23
|
||||
|
11
Makefile
11
Makefile
@@ -1,12 +1,12 @@
|
||||
default: update
|
||||
|
||||
update: update-readme update-latest
|
||||
update: compile update-readme update-latest
|
||||
|
||||
update-latest:
|
||||
./youtube-dl --version > LATEST_VERSION
|
||||
./youtube-dl.dev --version > LATEST_VERSION
|
||||
|
||||
update-readme:
|
||||
@options=$$(COLUMNS=80 ./youtube-dl --help | sed -e '1,/.*General Options.*/ d' -e 's/^\W\{2\}\(\w\)/### \1/') && \
|
||||
@options=$$(COLUMNS=80 ./youtube-dl.dev --help | sed -e '1,/.*General Options.*/ d' -e 's/^\W\{2\}\(\w\)/### \1/') && \
|
||||
header=$$(sed -e '/.*## OPTIONS/,$$ d' README.md) && \
|
||||
footer=$$(sed -e '1,/.*## FAQ/ d' README.md) && \
|
||||
echo "$${header}" > README.md && \
|
||||
@@ -15,6 +15,7 @@ update-readme:
|
||||
echo -e '\n## FAQ' >> README.md && \
|
||||
echo "$${footer}" >> README.md
|
||||
|
||||
compile:
|
||||
cp youtube_dl/__init__.py youtube-dl
|
||||
|
||||
|
||||
.PHONY: default update update-latest update-readme
|
||||
.PHONY: default compile update update-latest update-readme
|
||||
|
11
README.md
11
README.md
@@ -33,13 +33,17 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
-t, --title use title in file name
|
||||
-l, --literal use literal title in file name
|
||||
-A, --auto-number number downloaded files starting from 00000
|
||||
-o, --output TEMPLATE output filename template
|
||||
-o, --output TEMPLATE output filename template. Use %(stitle)s to get the
|
||||
title, %(uploader)s for the uploader name,
|
||||
%(autonumber)s to get an automatically incremented
|
||||
number, %(ext)s for the filename extension, and %%
|
||||
for a literal percent
|
||||
-a, --batch-file FILE file containing URLs to download ('-' for stdin)
|
||||
-w, --no-overwrites do not overwrite files
|
||||
-c, --continue resume partially downloaded files
|
||||
--no-continue do not resume partially downloaded files (restart
|
||||
from beginning)
|
||||
--cookies FILE file to dump cookie jar to
|
||||
--cookies FILE file to read cookies from and dump cookie jar in
|
||||
--no-part do not use .part files
|
||||
--no-mtime do not use the Last-modified header to set the file
|
||||
modification time
|
||||
@@ -64,6 +68,7 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
-f, --format FORMAT video format code
|
||||
--all-formats download all available video formats
|
||||
--max-quality FORMAT highest quality format to download
|
||||
-F, --list-formats list all available formats (currently youtube only)
|
||||
|
||||
### Authentication Options:
|
||||
-u, --username USERNAME account username
|
||||
@@ -73,7 +78,7 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
### Post-processing Options:
|
||||
--extract-audio convert video files to audio-only files (requires
|
||||
ffmpeg and ffprobe)
|
||||
--audio-format FORMAT "best", "aac" or "mp3"; best by default
|
||||
--audio-format FORMAT "best", "aac", "vorbis" or "mp3"; best by default
|
||||
--audio-quality QUALITY ffmpeg audio bitrate specification, 128k by default
|
||||
-k, --keep-video keeps the video file on disk after the post-
|
||||
processing; the video is erased by default
|
||||
|
29
test/test_div.py
Normal file
29
test/test_div.py
Normal file
@@ -0,0 +1,29 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Various small unit tests
|
||||
|
||||
import os,sys
|
||||
sys.path.append(os.path.dirname(os.path.dirname(__file__)))
|
||||
|
||||
import youtube_dl
|
||||
|
||||
def test_simplify_title():
|
||||
assert youtube_dl._simplify_title(u'abc') == u'abc'
|
||||
assert youtube_dl._simplify_title(u'abc_d-e') == u'abc_d-e'
|
||||
|
||||
assert youtube_dl._simplify_title(u'123') == u'123'
|
||||
|
||||
assert u'/' not in youtube_dl._simplify_title(u'abc/de')
|
||||
assert u'abc' in youtube_dl._simplify_title(u'abc/de')
|
||||
assert u'de' in youtube_dl._simplify_title(u'abc/de')
|
||||
assert u'/' not in youtube_dl._simplify_title(u'abc/de///')
|
||||
|
||||
assert u'\\' not in youtube_dl._simplify_title(u'abc\\de')
|
||||
assert u'abc' in youtube_dl._simplify_title(u'abc\\de')
|
||||
assert u'de' in youtube_dl._simplify_title(u'abc\\de')
|
||||
|
||||
assert youtube_dl._simplify_title(u'ä') == u'ä'
|
||||
assert youtube_dl._simplify_title(u'кириллица') == u'кириллица'
|
||||
|
||||
# Strip underlines
|
||||
assert youtube_dl._simplify_title(u'\'a_') == u'a'
|
569
youtube-dl
569
youtube-dl
@@ -12,10 +12,12 @@ __author__ = (
|
||||
'Rogério Brito',
|
||||
'Philipp Hagemeister',
|
||||
'Sören Schulze',
|
||||
'Kevin Ngo',
|
||||
'Ori Avtalion',
|
||||
)
|
||||
|
||||
__license__ = 'Public Domain'
|
||||
__version__ = '2011.09.17'
|
||||
__version__ = '2011.11.23'
|
||||
|
||||
UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
|
||||
|
||||
@@ -77,8 +79,6 @@ std_headers = {
|
||||
'Accept-Language': 'en-us,en;q=0.5',
|
||||
}
|
||||
|
||||
simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
|
||||
|
||||
try:
|
||||
import json
|
||||
except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson):
|
||||
@@ -277,6 +277,9 @@ def timeconvert(timestr):
|
||||
timestamp = email.utils.mktime_tz(timetuple)
|
||||
return timestamp
|
||||
|
||||
def _simplify_title(title):
|
||||
expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
|
||||
return expr.sub(u'_', title).strip(u'_')
|
||||
|
||||
class DownloadError(Exception):
|
||||
"""Download Error exception.
|
||||
@@ -766,7 +769,8 @@ class FileDownloader(object):
|
||||
try:
|
||||
infof = open(infofn, 'wb')
|
||||
try:
|
||||
json.dump(info_dict, infof)
|
||||
json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
|
||||
json.dump(json_info_dict, infof)
|
||||
finally:
|
||||
infof.close()
|
||||
except (OSError, IOError):
|
||||
@@ -905,6 +909,8 @@ class FileDownloader(object):
|
||||
while count <= retries:
|
||||
# Establish connection
|
||||
try:
|
||||
if count == 0 and 'urlhandle' in info_dict:
|
||||
data = info_dict['urlhandle']
|
||||
data = urllib2.urlopen(request)
|
||||
break
|
||||
except (urllib2.HTTPError, ), err:
|
||||
@@ -982,9 +988,12 @@ class FileDownloader(object):
|
||||
block_size = self.best_block_size(after - before, len(data_block))
|
||||
|
||||
# Progress message
|
||||
speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
|
||||
if data_len is None:
|
||||
self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA')
|
||||
else:
|
||||
percent_str = self.calc_percent(byte_counter, data_len)
|
||||
eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
|
||||
speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
|
||||
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
|
||||
|
||||
# Apply rate limit
|
||||
@@ -1079,13 +1088,13 @@ class InfoExtractor(object):
|
||||
class YoutubeIE(InfoExtractor):
|
||||
"""Information extractor for youtube.com."""
|
||||
|
||||
_VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
|
||||
_VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
|
||||
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
|
||||
_LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
|
||||
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
|
||||
_NETRC_MACHINE = 'youtube'
|
||||
# Listed in order of quality
|
||||
_available_formats = ['38', '37', '45', '22', '43', '35', '34', '18', '6', '5', '17', '13']
|
||||
_available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
|
||||
_video_extensions = {
|
||||
'13': '3gp',
|
||||
'17': 'mp4',
|
||||
@@ -1094,8 +1103,24 @@ class YoutubeIE(InfoExtractor):
|
||||
'37': 'mp4',
|
||||
'38': 'video', # You actually don't know if this will be MOV, AVI or whatever
|
||||
'43': 'webm',
|
||||
'44': 'webm',
|
||||
'45': 'webm',
|
||||
}
|
||||
_video_dimensions = {
|
||||
'5': '240x400',
|
||||
'6': '???',
|
||||
'13': '???',
|
||||
'17': '144x176',
|
||||
'18': '360x640',
|
||||
'22': '720x1280',
|
||||
'34': '360x640',
|
||||
'35': '480x854',
|
||||
'37': '1080x1920',
|
||||
'38': '3072x4096',
|
||||
'43': '360x640',
|
||||
'44': '480x854',
|
||||
'45': '720x1280',
|
||||
}
|
||||
IE_NAME = u'youtube'
|
||||
|
||||
def report_lang(self):
|
||||
@@ -1130,6 +1155,11 @@ class YoutubeIE(InfoExtractor):
|
||||
"""Indicate the download will use the RTMP protocol."""
|
||||
self._downloader.to_screen(u'[youtube] RTMP download detected')
|
||||
|
||||
def _print_formats(self, formats):
|
||||
print 'Available formats:'
|
||||
for x in formats:
|
||||
print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))
|
||||
|
||||
def _real_initialize(self):
|
||||
if self._downloader is None:
|
||||
return
|
||||
@@ -1209,7 +1239,7 @@ class YoutubeIE(InfoExtractor):
|
||||
|
||||
# Get video webpage
|
||||
self.report_video_webpage_download(video_id)
|
||||
request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
|
||||
request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
|
||||
try:
|
||||
video_webpage = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
@@ -1262,8 +1292,7 @@ class YoutubeIE(InfoExtractor):
|
||||
video_title = sanitize_title(video_title)
|
||||
|
||||
# simplified title
|
||||
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
|
||||
simple_title = simple_title.strip(ur'_')
|
||||
simple_title = _simplify_title(video_title)
|
||||
|
||||
# thumbnail image
|
||||
if 'thumbnail_url' not in video_info:
|
||||
@@ -1323,6 +1352,9 @@ class YoutubeIE(InfoExtractor):
|
||||
if len(existing_formats) == 0:
|
||||
self._downloader.trouble(u'ERROR: no known formats available for video')
|
||||
return
|
||||
if self._downloader.params.get('listformats', None):
|
||||
self._print_formats(existing_formats)
|
||||
return
|
||||
if req_format is None or req_format == 'best':
|
||||
video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
|
||||
elif req_format == 'worst':
|
||||
@@ -1530,9 +1562,6 @@ class DailymotionIE(InfoExtractor):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
|
||||
|
||||
def _real_initialize(self):
|
||||
return
|
||||
|
||||
def _real_extract(self, url):
|
||||
# Extract id and simplified title from URL
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
@@ -1621,9 +1650,6 @@ class GoogleIE(InfoExtractor):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
|
||||
|
||||
def _real_initialize(self):
|
||||
return
|
||||
|
||||
def _real_extract(self, url):
|
||||
# Extract id from URL
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
@@ -1667,7 +1693,7 @@ class GoogleIE(InfoExtractor):
|
||||
return
|
||||
video_title = mobj.group(1).decode('utf-8')
|
||||
video_title = sanitize_title(video_title)
|
||||
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
|
||||
simple_title = _simplify_title(video_title)
|
||||
|
||||
# Extract video description
|
||||
mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
|
||||
@@ -1728,9 +1754,6 @@ class PhotobucketIE(InfoExtractor):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
|
||||
|
||||
def _real_initialize(self):
|
||||
return
|
||||
|
||||
def _real_extract(self, url):
|
||||
# Extract id from URL
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
@@ -1769,7 +1792,7 @@ class PhotobucketIE(InfoExtractor):
|
||||
return
|
||||
video_title = mobj.group(1).decode('utf-8')
|
||||
video_title = sanitize_title(video_title)
|
||||
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
|
||||
simple_title = _simplify_title(vide_title)
|
||||
|
||||
video_uploader = mobj.group(2).decode('utf-8')
|
||||
|
||||
@@ -1810,9 +1833,6 @@ class YahooIE(InfoExtractor):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
|
||||
|
||||
def _real_initialize(self):
|
||||
return
|
||||
|
||||
def _real_extract(self, url, new_video=True):
|
||||
# Extract ID from URL
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
@@ -1866,7 +1886,7 @@ class YahooIE(InfoExtractor):
|
||||
self._downloader.trouble(u'ERROR: unable to extract video title')
|
||||
return
|
||||
video_title = mobj.group(1).decode('utf-8')
|
||||
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
|
||||
simple_title = _simplify_title(video_title)
|
||||
|
||||
mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
|
||||
if mobj is None:
|
||||
@@ -1963,9 +1983,6 @@ class VimeoIE(InfoExtractor):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
|
||||
|
||||
def _real_initialize(self):
|
||||
return
|
||||
|
||||
def _real_extract(self, url, new_video=True):
|
||||
# Extract ID from URL
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
@@ -1997,7 +2014,7 @@ class VimeoIE(InfoExtractor):
|
||||
self._downloader.trouble(u'ERROR: unable to extract video title')
|
||||
return
|
||||
video_title = mobj.group(1).decode('utf-8')
|
||||
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
|
||||
simple_title = _simplify_title(video_title)
|
||||
|
||||
# Extract uploader
|
||||
mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage)
|
||||
@@ -2029,6 +2046,18 @@ class VimeoIE(InfoExtractor):
|
||||
return
|
||||
sig = mobj.group(1).decode('utf-8')
|
||||
|
||||
# Vimeo specific: extract video quality information
|
||||
mobj = re.search(r'<isHD>(\d+)</isHD>', webpage)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract video quality information')
|
||||
return
|
||||
quality = mobj.group(1).decode('utf-8')
|
||||
|
||||
if int(quality) == 1:
|
||||
quality = 'hd'
|
||||
else:
|
||||
quality = 'sd'
|
||||
|
||||
# Vimeo specific: Extract request signature expiration
|
||||
mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage)
|
||||
if mobj is None:
|
||||
@@ -2036,7 +2065,7 @@ class VimeoIE(InfoExtractor):
|
||||
return
|
||||
sig_exp = mobj.group(1).decode('utf-8')
|
||||
|
||||
video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s" % (video_id, sig, sig_exp)
|
||||
video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s/?q=%s" % (video_id, sig, sig_exp, quality)
|
||||
|
||||
try:
|
||||
# Process video information
|
||||
@@ -2076,9 +2105,6 @@ class GenericIE(InfoExtractor):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
|
||||
|
||||
def _real_initialize(self):
|
||||
return
|
||||
|
||||
def _real_extract(self, url):
|
||||
# At this point we have a new video
|
||||
self._downloader.increment_downloads()
|
||||
@@ -2132,7 +2158,7 @@ class GenericIE(InfoExtractor):
|
||||
return
|
||||
video_title = mobj.group(1).decode('utf-8')
|
||||
video_title = sanitize_title(video_title)
|
||||
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
|
||||
simple_title = _simplify_title(video_title)
|
||||
|
||||
# video uploader is domain name
|
||||
mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
|
||||
@@ -2428,7 +2454,7 @@ class YahooSearchIE(InfoExtractor):
|
||||
class YoutubePlaylistIE(InfoExtractor):
|
||||
"""Information Extractor for YouTube playlists."""
|
||||
|
||||
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
|
||||
_VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
|
||||
_TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
|
||||
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
|
||||
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
|
||||
@@ -2472,7 +2498,8 @@ class YoutubePlaylistIE(InfoExtractor):
|
||||
|
||||
while True:
|
||||
self.report_download_page(playlist_id, pagenum)
|
||||
request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
|
||||
url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)
|
||||
request = urllib2.Request(url)
|
||||
try:
|
||||
page = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
@@ -2502,11 +2529,11 @@ class YoutubePlaylistIE(InfoExtractor):
|
||||
class YoutubeUserIE(InfoExtractor):
|
||||
"""Information Extractor for YouTube users."""
|
||||
|
||||
_VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
|
||||
_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
|
||||
_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
|
||||
_GDATA_PAGE_SIZE = 50
|
||||
_GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
|
||||
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
|
||||
_VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'
|
||||
_youtube_ie = None
|
||||
IE_NAME = u'youtube:user'
|
||||
|
||||
@@ -2590,7 +2617,7 @@ class YoutubeUserIE(InfoExtractor):
|
||||
class DepositFilesIE(InfoExtractor):
|
||||
"""Information extractor for depositfiles.com"""
|
||||
|
||||
_VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)'
|
||||
_VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
|
||||
IE_NAME = u'DepositFiles'
|
||||
|
||||
def __init__(self, downloader=None):
|
||||
@@ -2604,9 +2631,6 @@ class DepositFilesIE(InfoExtractor):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
|
||||
|
||||
def _real_initialize(self):
|
||||
return
|
||||
|
||||
def _real_extract(self, url):
|
||||
# At this point we have a new file
|
||||
self._downloader.increment_downloads()
|
||||
@@ -2667,11 +2691,12 @@ class DepositFilesIE(InfoExtractor):
|
||||
class FacebookIE(InfoExtractor):
|
||||
"""Information Extractor for Facebook"""
|
||||
|
||||
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
|
||||
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
|
||||
_LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
|
||||
_NETRC_MACHINE = 'facebook'
|
||||
_available_formats = ['highqual', 'lowqual']
|
||||
_available_formats = ['video', 'highqual', 'lowqual']
|
||||
_video_extensions = {
|
||||
'video': 'mp4',
|
||||
'highqual': 'mp4',
|
||||
'lowqual': 'mp4',
|
||||
}
|
||||
@@ -2699,10 +2724,9 @@ class FacebookIE(InfoExtractor):
|
||||
def _parse_page(self, video_webpage):
|
||||
"""Extract video information from page"""
|
||||
# General data
|
||||
data = {'title': r'class="video_title datawrap">(.*?)</',
|
||||
data = {'title': r'\("video_title", "(.*?)"\)',
|
||||
'description': r'<div class="datawrap">(.*?)</div>',
|
||||
'owner': r'\("video_owner_name", "(.*?)"\)',
|
||||
'upload_date': r'data-date="(.*?)"',
|
||||
'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)',
|
||||
}
|
||||
video_info = {}
|
||||
@@ -2804,9 +2828,7 @@ class FacebookIE(InfoExtractor):
|
||||
video_title = video_title.decode('utf-8')
|
||||
video_title = sanitize_title(video_title)
|
||||
|
||||
# simplified title
|
||||
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
|
||||
simple_title = simple_title.strip(ur'_')
|
||||
simple_title = _simplify_title(video_title)
|
||||
|
||||
# thumbnail image
|
||||
if 'thumbnail' not in video_info:
|
||||
@@ -2891,12 +2913,11 @@ class BlipTVIE(InfoExtractor):
|
||||
|
||||
def report_extraction(self, file_id):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[blip.tv] %s: Extracting information' % file_id)
|
||||
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
|
||||
|
||||
def _simplify_title(self, title):
|
||||
res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
|
||||
res = res.strip(ur'_')
|
||||
return res
|
||||
def report_direct_download(self, title):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
@@ -2911,11 +2932,33 @@ class BlipTVIE(InfoExtractor):
|
||||
json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
|
||||
request = urllib2.Request(json_url)
|
||||
self.report_extraction(mobj.group(1))
|
||||
info = None
|
||||
try:
|
||||
json_code = urllib2.urlopen(request).read()
|
||||
urlh = urllib2.urlopen(request)
|
||||
if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
|
||||
basename = url.split('/')[-1]
|
||||
title,ext = os.path.splitext(basename)
|
||||
title = title.decode('UTF-8')
|
||||
ext = ext.replace('.', '')
|
||||
self.report_direct_download(title)
|
||||
info = {
|
||||
'id': title,
|
||||
'url': url,
|
||||
'title': title,
|
||||
'stitle': _simplify_title(title),
|
||||
'ext': ext,
|
||||
'urlhandle': urlh
|
||||
}
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
|
||||
return
|
||||
if info is None: # Regular URL
|
||||
try:
|
||||
json_code = urlh.read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err))
|
||||
return
|
||||
|
||||
try:
|
||||
json_data = json.loads(json_code)
|
||||
if 'Post' in json_data:
|
||||
@@ -2930,15 +2973,13 @@ class BlipTVIE(InfoExtractor):
|
||||
raise ValueError('Can not determine filename extension')
|
||||
ext = umobj.group(1)
|
||||
|
||||
self._downloader.increment_downloads()
|
||||
|
||||
info = {
|
||||
'id': data['item_id'],
|
||||
'url': video_url,
|
||||
'uploader': data['display_name'],
|
||||
'upload_date': upload_date,
|
||||
'title': data['title'],
|
||||
'stitle': self._simplify_title(data['title']),
|
||||
'stitle': _simplify_title(data['title']),
|
||||
'ext': ext,
|
||||
'format': data['media']['mimeType'],
|
||||
'thumbnail': data['thumbnailUrl'],
|
||||
@@ -2949,6 +2990,8 @@ class BlipTVIE(InfoExtractor):
|
||||
self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
|
||||
return
|
||||
|
||||
self._downloader.increment_downloads()
|
||||
|
||||
try:
|
||||
self._downloader.process_info(info)
|
||||
except UnavailableVideoError, err:
|
||||
@@ -2972,9 +3015,6 @@ class MyVideoIE(InfoExtractor):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
|
||||
|
||||
def _real_initialize(self):
|
||||
return
|
||||
|
||||
def _real_extract(self,url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
@@ -2982,10 +3022,6 @@ class MyVideoIE(InfoExtractor):
|
||||
return
|
||||
|
||||
video_id = mobj.group(1)
|
||||
simple_title = mobj.group(2).decode('utf-8')
|
||||
# should actually not be necessary
|
||||
simple_title = sanitize_title(simple_title)
|
||||
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', simple_title)
|
||||
|
||||
# Get video webpage
|
||||
request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id)
|
||||
@@ -3012,8 +3048,9 @@ class MyVideoIE(InfoExtractor):
|
||||
video_title = mobj.group(1)
|
||||
video_title = sanitize_title(video_title)
|
||||
|
||||
simple_title = _simplify_title(video_title)
|
||||
|
||||
try:
|
||||
print(video_url)
|
||||
self._downloader.process_info({
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
@@ -3046,11 +3083,6 @@ class ComedyCentralIE(InfoExtractor):
|
||||
def report_player_url(self, episode_id):
|
||||
self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
|
||||
|
||||
def _simplify_title(self, title):
|
||||
res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
|
||||
res = res.strip(ur'_')
|
||||
return res
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
@@ -3059,9 +3091,9 @@ class ComedyCentralIE(InfoExtractor):
|
||||
|
||||
if mobj.group('shortname'):
|
||||
if mobj.group('shortname') in ('tds', 'thedailyshow'):
|
||||
url = 'http://www.thedailyshow.com/full-episodes/'
|
||||
url = u'http://www.thedailyshow.com/full-episodes/'
|
||||
else:
|
||||
url = 'http://www.colbertnation.com/full-episodes/'
|
||||
url = u'http://www.colbertnation.com/full-episodes/'
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
assert mobj is not None
|
||||
|
||||
@@ -3147,14 +3179,14 @@ class ComedyCentralIE(InfoExtractor):
|
||||
|
||||
self._downloader.increment_downloads()
|
||||
|
||||
effTitle = showId + '-' + epTitle
|
||||
effTitle = showId + u'-' + epTitle
|
||||
info = {
|
||||
'id': shortMediaId,
|
||||
'url': video_url,
|
||||
'uploader': showId,
|
||||
'upload_date': officialDate,
|
||||
'title': effTitle,
|
||||
'stitle': self._simplify_title(effTitle),
|
||||
'stitle': _simplify_title(effTitle),
|
||||
'ext': 'mp4',
|
||||
'format': format,
|
||||
'thumbnail': None,
|
||||
@@ -3172,7 +3204,7 @@ class ComedyCentralIE(InfoExtractor):
|
||||
class EscapistIE(InfoExtractor):
|
||||
"""Information extractor for The Escapist """
|
||||
|
||||
_VALID_URL = r'^(https?://)?(www\.)escapistmagazine.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?].*$'
|
||||
_VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
|
||||
IE_NAME = u'escapist'
|
||||
|
||||
def report_extraction(self, showName):
|
||||
@@ -3181,11 +3213,6 @@ class EscapistIE(InfoExtractor):
|
||||
def report_config_download(self, showName):
|
||||
self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
|
||||
|
||||
def _simplify_title(self, title):
|
||||
res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
|
||||
res = res.strip(ur'_')
|
||||
return res
|
||||
|
||||
def _real_extract(self, url):
|
||||
htmlParser = HTMLParser.HTMLParser()
|
||||
|
||||
@@ -3238,7 +3265,7 @@ class EscapistIE(InfoExtractor):
|
||||
'uploader': showName,
|
||||
'upload_date': None,
|
||||
'title': showName,
|
||||
'stitle': self._simplify_title(showName),
|
||||
'stitle': _simplify_title(showName),
|
||||
'ext': 'flv',
|
||||
'format': 'flv',
|
||||
'thumbnail': imgUrl,
|
||||
@@ -3252,6 +3279,336 @@ class EscapistIE(InfoExtractor):
|
||||
self._downloader.trouble(u'\nERROR: unable to download ' + videoId)
|
||||
|
||||
|
||||
class CollegeHumorIE(InfoExtractor):
|
||||
"""Information extractor for collegehumor.com"""
|
||||
|
||||
_VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
|
||||
IE_NAME = u'collegehumor'
|
||||
|
||||
def report_webpage(self, video_id):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
|
||||
|
||||
def report_extraction(self, video_id):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
|
||||
|
||||
def _real_extract(self, url):
|
||||
htmlParser = HTMLParser.HTMLParser()
|
||||
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||
return
|
||||
video_id = mobj.group('videoid')
|
||||
|
||||
self.report_webpage(video_id)
|
||||
request = urllib2.Request(url)
|
||||
try:
|
||||
webpage = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
|
||||
return
|
||||
|
||||
m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage)
|
||||
if m is None:
|
||||
self._downloader.trouble(u'ERROR: Cannot extract internal video ID')
|
||||
return
|
||||
internal_video_id = m.group('internalvideoid')
|
||||
|
||||
info = {
|
||||
'id': video_id,
|
||||
'internal_id': internal_video_id,
|
||||
}
|
||||
|
||||
self.report_extraction(video_id)
|
||||
xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id
|
||||
try:
|
||||
metaXml = urllib2.urlopen(xmlUrl).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err))
|
||||
return
|
||||
|
||||
mdoc = xml.etree.ElementTree.fromstring(metaXml)
|
||||
try:
|
||||
videoNode = mdoc.findall('./video')[0]
|
||||
info['description'] = videoNode.findall('./description')[0].text
|
||||
info['title'] = videoNode.findall('./caption')[0].text
|
||||
info['stitle'] = _simplify_title(info['title'])
|
||||
info['url'] = videoNode.findall('./file')[0].text
|
||||
info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
|
||||
info['ext'] = info['url'].rpartition('.')[2]
|
||||
info['format'] = info['ext']
|
||||
except IndexError:
|
||||
self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
|
||||
return
|
||||
|
||||
self._downloader.increment_downloads()
|
||||
|
||||
try:
|
||||
self._downloader.process_info(info)
|
||||
except UnavailableVideoError, err:
|
||||
self._downloader.trouble(u'\nERROR: unable to download video')
|
||||
|
||||
|
||||
class XVideosIE(InfoExtractor):
|
||||
"""Information extractor for xvideos.com"""
|
||||
|
||||
_VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
|
||||
IE_NAME = u'xvideos'
|
||||
|
||||
def report_webpage(self, video_id):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
|
||||
|
||||
def report_extraction(self, video_id):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
|
||||
|
||||
def _real_extract(self, url):
|
||||
htmlParser = HTMLParser.HTMLParser()
|
||||
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||
return
|
||||
video_id = mobj.group(1).decode('utf-8')
|
||||
|
||||
self.report_webpage(video_id)
|
||||
|
||||
request = urllib2.Request(r'http://www.xvideos.com/video' + video_id)
|
||||
try:
|
||||
webpage = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
|
||||
return
|
||||
|
||||
self.report_extraction(video_id)
|
||||
|
||||
|
||||
# Extract video URL
|
||||
mobj = re.search(r'flv_url=(.+?)&', webpage)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract video url')
|
||||
return
|
||||
video_url = urllib2.unquote(mobj.group(1).decode('utf-8'))
|
||||
|
||||
|
||||
# Extract title
|
||||
mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract video title')
|
||||
return
|
||||
video_title = mobj.group(1).decode('utf-8')
|
||||
|
||||
|
||||
# Extract video thumbnail
|
||||
mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
|
||||
return
|
||||
video_thumbnail = mobj.group(1).decode('utf-8')
|
||||
|
||||
|
||||
|
||||
self._downloader.increment_downloads()
|
||||
info = {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'uploader': None,
|
||||
'upload_date': None,
|
||||
'title': video_title,
|
||||
'stitle': _simplify_title(video_title),
|
||||
'ext': 'flv',
|
||||
'format': 'flv',
|
||||
'thumbnail': video_thumbnail,
|
||||
'description': None,
|
||||
'player_url': None,
|
||||
}
|
||||
|
||||
try:
|
||||
self._downloader.process_info(info)
|
||||
except UnavailableVideoError, err:
|
||||
self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
|
||||
|
||||
|
||||
class SoundcloudIE(InfoExtractor):
|
||||
"""Information extractor for soundcloud.com
|
||||
To access the media, the uid of the song and a stream token
|
||||
must be extracted from the page source and the script must make
|
||||
a request to media.soundcloud.com/crossdomain.xml. Then
|
||||
the media can be grabbed by requesting from an url composed
|
||||
of the stream token and uid
|
||||
"""
|
||||
|
||||
_VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
|
||||
IE_NAME = u'soundcloud'
|
||||
|
||||
def __init__(self, downloader=None):
|
||||
InfoExtractor.__init__(self, downloader)
|
||||
|
||||
def report_webpage(self, video_id):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
|
||||
|
||||
def report_extraction(self, video_id):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
|
||||
|
||||
def _real_extract(self, url):
|
||||
htmlParser = HTMLParser.HTMLParser()
|
||||
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||
return
|
||||
|
||||
# extract uploader (which is in the url)
|
||||
uploader = mobj.group(1).decode('utf-8')
|
||||
# extract simple title (uploader + slug of song title)
|
||||
slug_title = mobj.group(2).decode('utf-8')
|
||||
simple_title = uploader + '-' + slug_title
|
||||
|
||||
self.report_webpage('%s/%s' % (uploader, slug_title))
|
||||
|
||||
request = urllib2.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title))
|
||||
try:
|
||||
webpage = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
|
||||
return
|
||||
|
||||
self.report_extraction('%s/%s' % (uploader, slug_title))
|
||||
|
||||
# extract uid and stream token that soundcloud hands out for access
|
||||
mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage)
|
||||
if mobj:
|
||||
video_id = mobj.group(1)
|
||||
stream_token = mobj.group(2)
|
||||
|
||||
# extract unsimplified title
|
||||
mobj = re.search('"title":"(.*?)",', webpage)
|
||||
if mobj:
|
||||
title = mobj.group(1)
|
||||
|
||||
# construct media url (with uid/token)
|
||||
mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s"
|
||||
mediaURL = mediaURL % (video_id, stream_token)
|
||||
|
||||
# description
|
||||
description = u'No description available'
|
||||
mobj = re.search('track-description-value"><p>(.*?)</p>', webpage)
|
||||
if mobj:
|
||||
description = mobj.group(1)
|
||||
|
||||
# upload date
|
||||
upload_date = None
|
||||
mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage)
|
||||
if mobj:
|
||||
try:
|
||||
upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
|
||||
except Exception, e:
|
||||
print str(e)
|
||||
|
||||
# for soundcloud, a request to a cross domain is required for cookies
|
||||
request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers)
|
||||
|
||||
try:
|
||||
self._downloader.process_info({
|
||||
'id': video_id.decode('utf-8'),
|
||||
'url': mediaURL,
|
||||
'uploader': uploader.decode('utf-8'),
|
||||
'upload_date': upload_date,
|
||||
'title': simple_title.decode('utf-8'),
|
||||
'stitle': simple_title.decode('utf-8'),
|
||||
'ext': u'mp3',
|
||||
'format': u'NA',
|
||||
'player_url': None,
|
||||
'description': description.decode('utf-8')
|
||||
})
|
||||
except UnavailableVideoError:
|
||||
self._downloader.trouble(u'\nERROR: unable to download video')
|
||||
|
||||
|
||||
class InfoQIE(InfoExtractor):
|
||||
"""Information extractor for infoq.com"""
|
||||
|
||||
_VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
|
||||
IE_NAME = u'infoq'
|
||||
|
||||
def report_webpage(self, video_id):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
|
||||
|
||||
def report_extraction(self, video_id):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
|
||||
|
||||
def _real_extract(self, url):
|
||||
htmlParser = HTMLParser.HTMLParser()
|
||||
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||
return
|
||||
|
||||
self.report_webpage(url)
|
||||
|
||||
request = urllib2.Request(url)
|
||||
try:
|
||||
webpage = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
|
||||
return
|
||||
|
||||
self.report_extraction(url)
|
||||
|
||||
|
||||
# Extract video URL
|
||||
mobj = re.search(r"jsclassref='([^']*)'", webpage)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract video url')
|
||||
return
|
||||
video_url = 'rtmpe://video.infoq.com/cfx/st/' + urllib2.unquote(mobj.group(1).decode('base64'))
|
||||
|
||||
|
||||
# Extract title
|
||||
mobj = re.search(r'contentTitle = "(.*?)";', webpage)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract video title')
|
||||
return
|
||||
video_title = mobj.group(1).decode('utf-8')
|
||||
|
||||
# Extract description
|
||||
video_description = u'No description available.'
|
||||
mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage)
|
||||
if mobj is not None:
|
||||
video_description = mobj.group(1).decode('utf-8')
|
||||
|
||||
video_filename = video_url.split('/')[-1]
|
||||
video_id, extension = video_filename.split('.')
|
||||
|
||||
self._downloader.increment_downloads()
|
||||
info = {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'uploader': None,
|
||||
'upload_date': None,
|
||||
'title': video_title,
|
||||
'stitle': _simplify_title(video_title),
|
||||
'ext': extension,
|
||||
'format': extension, # Extension is always(?) mp4, but seems to be flv
|
||||
'thumbnail': None,
|
||||
'description': video_description,
|
||||
'player_url': None,
|
||||
}
|
||||
|
||||
try:
|
||||
self._downloader.process_info(info)
|
||||
except UnavailableVideoError, err:
|
||||
self._downloader.trouble(u'\nERROR: unable to download ' + video_url)
|
||||
|
||||
|
||||
|
||||
class PostProcessor(object):
|
||||
"""Post Processor class.
|
||||
@@ -3347,12 +3704,14 @@ class FFmpegExtractAudioPP(PostProcessor):
|
||||
|
||||
more_opts = []
|
||||
if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
|
||||
if filecodec == 'aac' or filecodec == 'mp3':
|
||||
if filecodec in ['aac', 'mp3', 'vorbis']:
|
||||
# Lossless if possible
|
||||
acodec = 'copy'
|
||||
extension = filecodec
|
||||
if filecodec == 'aac':
|
||||
more_opts = ['-f', 'adts']
|
||||
if filecodec == 'vorbis':
|
||||
extension = 'ogg'
|
||||
else:
|
||||
# MP3 otherwise.
|
||||
acodec = 'libmp3lame'
|
||||
@@ -3362,13 +3721,15 @@ class FFmpegExtractAudioPP(PostProcessor):
|
||||
more_opts += ['-ab', self._preferredquality]
|
||||
else:
|
||||
# We convert the audio (lossy)
|
||||
acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec]
|
||||
acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'vorbis': 'libvorbis'}[self._preferredcodec]
|
||||
extension = self._preferredcodec
|
||||
more_opts = []
|
||||
if self._preferredquality is not None:
|
||||
more_opts += ['-ab', self._preferredquality]
|
||||
if self._preferredcodec == 'aac':
|
||||
more_opts += ['-f', 'adts']
|
||||
if self._preferredcodec == 'vorbis':
|
||||
extension = 'ogg'
|
||||
|
||||
(prefix, ext) = os.path.splitext(path)
|
||||
new_path = prefix + '.' + extension
|
||||
@@ -3409,6 +3770,11 @@ def updateSelf(downloader, filename):
|
||||
try:
|
||||
urlh = urllib.urlopen(UPDATE_URL)
|
||||
newcontent = urlh.read()
|
||||
|
||||
vmatch = re.search("__version__ = '([^']+)'", newcontent)
|
||||
if vmatch is not None and vmatch.group(1) == __version__:
|
||||
downloader.to_screen('youtube-dl is up-to-date (' + __version__ + ')')
|
||||
return
|
||||
finally:
|
||||
urlh.close()
|
||||
except (IOError, OSError), err:
|
||||
@@ -3423,7 +3789,7 @@ def updateSelf(downloader, filename):
|
||||
except (IOError, OSError), err:
|
||||
sys.exit('ERROR: unable to overwrite current version')
|
||||
|
||||
downloader.to_screen('Updated youtube-dl. Restart to use the new version.')
|
||||
downloader.to_screen('Updated youtube-dl. Restart youtube-dl to use the new version.')
|
||||
|
||||
def parseOpts():
|
||||
# Deferred imports
|
||||
@@ -3524,6 +3890,8 @@ def parseOpts():
|
||||
action='store_const', dest='format', help='download all available video formats', const='all')
|
||||
video_format.add_option('--max-quality',
|
||||
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
|
||||
video_format.add_option('-F', '--list-formats',
|
||||
action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
|
||||
|
||||
|
||||
verbosity.add_option('-q', '--quiet',
|
||||
@@ -3563,18 +3931,18 @@ def parseOpts():
|
||||
action='store_true', dest='autonumber',
|
||||
help='number downloaded files starting from 00000', default=False)
|
||||
filesystem.add_option('-o', '--output',
|
||||
dest='outtmpl', metavar='TEMPLATE', help='output filename template')
|
||||
dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, and %% for a literal percent')
|
||||
filesystem.add_option('-a', '--batch-file',
|
||||
dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
|
||||
filesystem.add_option('-w', '--no-overwrites',
|
||||
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
|
||||
filesystem.add_option('-c', '--continue',
|
||||
action='store_true', dest='continue_dl', help='resume partially downloaded files', default=True)
|
||||
action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
|
||||
filesystem.add_option('--no-continue',
|
||||
action='store_false', dest='continue_dl',
|
||||
help='do not resume partially downloaded files (restart from beginning)')
|
||||
filesystem.add_option('--cookies',
|
||||
dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
|
||||
dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
|
||||
filesystem.add_option('--no-part',
|
||||
action='store_true', dest='nopart', help='do not use .part files', default=False)
|
||||
filesystem.add_option('--no-mtime',
|
||||
@@ -3591,7 +3959,7 @@ def parseOpts():
|
||||
postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
|
||||
help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
|
||||
postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
|
||||
help='"best", "aac" or "mp3"; best by default')
|
||||
help='"best", "aac", "vorbis" or "mp3"; best by default')
|
||||
postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
|
||||
help='ffmpeg audio bitrate specification, 128k by default')
|
||||
postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
|
||||
@@ -3618,12 +3986,12 @@ def gen_extractors():
|
||||
google_ie = GoogleIE()
|
||||
yahoo_ie = YahooIE()
|
||||
return [
|
||||
youtube_ie,
|
||||
MetacafeIE(youtube_ie),
|
||||
DailymotionIE(),
|
||||
YoutubePlaylistIE(youtube_ie),
|
||||
YoutubeUserIE(youtube_ie),
|
||||
YoutubeSearchIE(youtube_ie),
|
||||
youtube_ie,
|
||||
MetacafeIE(youtube_ie),
|
||||
DailymotionIE(),
|
||||
google_ie,
|
||||
GoogleSearchIE(google_ie),
|
||||
PhotobucketIE(),
|
||||
@@ -3636,11 +4004,15 @@ def gen_extractors():
|
||||
MyVideoIE(),
|
||||
ComedyCentralIE(),
|
||||
EscapistIE(),
|
||||
CollegeHumorIE(),
|
||||
XVideosIE(),
|
||||
SoundcloudIE(),
|
||||
InfoQIE(),
|
||||
|
||||
GenericIE()
|
||||
]
|
||||
|
||||
def main():
|
||||
def _real_main():
|
||||
parser, opts, args = parseOpts()
|
||||
|
||||
# Open appropriate CookieJar
|
||||
@@ -3725,7 +4097,7 @@ def main():
|
||||
except (TypeError, ValueError), err:
|
||||
parser.error(u'invalid playlist end number specified')
|
||||
if opts.extractaudio:
|
||||
if opts.audioformat not in ['best', 'aac', 'mp3']:
|
||||
if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis']:
|
||||
parser.error(u'invalid audio format specified')
|
||||
|
||||
# File downloader
|
||||
@@ -3744,6 +4116,7 @@ def main():
|
||||
'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
|
||||
'format': opts.format,
|
||||
'format_limit': opts.format_limit,
|
||||
'listformats': opts.listformats,
|
||||
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
|
||||
or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
|
||||
or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
|
||||
@@ -3799,10 +4172,9 @@ def main():
|
||||
|
||||
sys.exit(retcode)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
def main():
|
||||
try:
|
||||
main()
|
||||
_real_main()
|
||||
except DownloadError:
|
||||
sys.exit(1)
|
||||
except SameFileError:
|
||||
@@ -3810,4 +4182,7 @@ if __name__ == '__main__':
|
||||
except KeyboardInterrupt:
|
||||
sys.exit(u'\nERROR: Interrupted by user')
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
|
||||
# vim: set ts=4 sw=4 sts=4 noet ai si filetype=python:
|
||||
|
6
youtube-dl.dev
Executable file
6
youtube-dl.dev
Executable file
@@ -0,0 +1,6 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import youtube_dl
|
||||
|
||||
youtube_dl.main()
|
4188
youtube_dl/__init__.py
Executable file
4188
youtube_dl/__init__.py
Executable file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user