R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #1 from rg3/master

Browse Source 
Update
This commit is contained in:
snipem 2015-04-12 10:45:11 +02:00
commit 0efc01e703
46 changed files with 1131 additions and 402 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
AUTHORS
View File

@ -120,3 +120,5 @@ Jeff Buchbinder
Amish Bhadeshia
Joram Schrijver
Will W.
Mohammad Teimori Pabandi
Roman Le Négrate

192
README.md
View File

@ -45,12 +45,12 @@ which means you can modify it, redistribute it or use it however you like.
youtube-dl [OPTIONS] URL [URL...]
# OPTIONS
-h, --help print this help text and exit
--version print program version and exit
-U, --update update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)
-i, --ignore-errors continue on download errors, for example to skip unavailable videos in a playlist
-h, --help Print this help text and exit
--version Print program version and exit
-U, --update Update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)
-i, --ignore-errors Continue on download errors, for example to skip unavailable videos in a playlist
--abort-on-error Abort downloading of further videos (in the playlist or the command line) if an error occurs
--dump-user-agent display the current browser identification
--dump-user-agent Display the current browser identification
--list-extractors List all supported extractors and the URLs they would handle
--extractor-descriptions Output descriptions of all supported extractors
--default-search PREFIX Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple".
@ -59,7 +59,7 @@ which means you can modify it, redistribute it or use it however you like.
--ignore-config Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: Do not read the user configuration
in ~/.config/youtube-dl/config (%APPDATA%/youtube-dl/config.txt on Windows)
--flat-playlist Do not extract the videos of a playlist, only list them.
--no-color Do not emit color codes in output.
--no-color Do not emit color codes in output
## Network Options:
--proxy URL Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection
@ -71,70 +71,70 @@ which means you can modify it, redistribute it or use it however you like.
not present) is used for the actual downloading. (experimental)
## Video Selection:
--playlist-start NUMBER playlist video to start at (default is 1)
--playlist-end NUMBER playlist video to end at (default is last)
--playlist-items ITEM_SPEC playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8"
--playlist-start NUMBER Playlist video to start at (default is 1)
--playlist-end NUMBER Playlist video to end at (default is last)
--playlist-items ITEM_SPEC Playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8"
if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will
download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.
--match-title REGEX download only matching titles (regex or caseless sub-string)
--reject-title REGEX skip download for matching titles (regex or caseless sub-string)
--match-title REGEX Download only matching titles (regex or caseless sub-string)
--reject-title REGEX Skip download for matching titles (regex or caseless sub-string)
--max-downloads NUMBER Abort after downloading NUMBER files
--min-filesize SIZE Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)
--max-filesize SIZE Do not download any videos larger than SIZE (e.g. 50k or 44.6m)
--date DATE download only videos uploaded in this date
--datebefore DATE download only videos uploaded on or before this date (i.e. inclusive)
--dateafter DATE download only videos uploaded on or after this date (i.e. inclusive)
--date DATE Download only videos uploaded in this date
--datebefore DATE Download only videos uploaded on or before this date (i.e. inclusive)
--dateafter DATE Download only videos uploaded on or after this date (i.e. inclusive)
--min-views COUNT Do not download any videos with less than COUNT views
--max-views COUNT Do not download any videos with more than COUNT views
--match-filter FILTER (Experimental) Generic video filter. Specify any key (see help for -o for a list of available keys) to match if the key is present,
--match-filter FILTER Generic video filter (experimental). Specify any key (see help for -o for a list of available keys) to match if the key is present,
!key to check if the key is not present,key > NUMBER (like "comment_count > 12", also works with >=, <, <=, !=, =) to compare against
a number, and & to require multiple matches. Values which are not known are excluded unless you put a question mark (?) after the
operator.For example, to only match videos that have been liked more than 100 times and disliked less than 50 times (or the dislike
functionality is not available at the given service), but who also have a description, use --match-filter "like_count > 100 &
dislike_count <? 50 & description" .
--no-playlist If the URL refers to a video and a playlist, download only the video.
--yes-playlist If the URL refers to a video and a playlist, download the playlist.
--age-limit YEARS download only videos suitable for the given age
--no-playlist Download only the video, if the URL refers to a video and a playlist.
--yes-playlist Download the playlist, if the URL refers to a video and a playlist.
--age-limit YEARS Download only videos suitable for the given age
--download-archive FILE Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.
--include-ads Download advertisements as well (experimental)
## Download Options:
-r, --rate-limit LIMIT maximum download rate in bytes per second (e.g. 50K or 4.2M)
-R, --retries RETRIES number of retries (default is 10), or "infinite".
--buffer-size SIZE size of download buffer (e.g. 1024 or 16K) (default is 1024)
--no-resize-buffer do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.
-r, --rate-limit LIMIT Maximum download rate in bytes per second (e.g. 50K or 4.2M)
-R, --retries RETRIES Number of retries (default is 10), or "infinite".
--buffer-size SIZE Size of download buffer (e.g. 1024 or 16K) (default is 1024)
--no-resize-buffer Do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.
--playlist-reverse Download playlist videos in reverse order
--xattr-set-filesize (experimental) set file xattribute ytdl.filesize with expected filesize
--hls-prefer-native (experimental) Use the native HLS downloader instead of ffmpeg.
--xattr-set-filesize Set file xattribute ytdl.filesize with expected filesize (experimental)
--hls-prefer-native Use the native HLS downloader instead of ffmpeg (experimental)
--external-downloader COMMAND Use the specified external downloader. Currently supports aria2c,curl,wget
--external-downloader-args ARGS Give these arguments to the external downloader.
--external-downloader-args ARGS Give these arguments to the external downloader
## Filesystem Options:
-a, --batch-file FILE file containing URLs to download ('-' for stdin)
--id use only video ID in file name
-o, --output TEMPLATE output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader
-a, --batch-file FILE File containing URLs to download ('-' for stdin)
--id Use only video ID in file name
-o, --output TEMPLATE Output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader
nickname if different, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(format)s for
the format description (like "22 - 1280x720" or "HD"), %(format_id)s for the unique id of the format (like Youtube's itags: "137"),
the format description (like "22 - 1280x720" or "HD"), %(format_id)s for the unique id of the format (like YouTube's itags: "137"),
%(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id,
%(playlist_title)s, %(playlist_id)s, or %(playlist)s (=title if present, ID otherwise) for the playlist the video is in,
%(playlist_index)s for the position in the playlist. %(height)s and %(width)s for the width and height of the video format.
%(resolution)s for a textual description of the resolution of the video format. %% for a literal percent. Use - to output to stdout.
Can also be used to download to a different directory, for example with -o '/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
--autonumber-size NUMBER Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given
--autonumber-size NUMBER Specify the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given
--restrict-filenames Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames
-A, --auto-number [deprecated; use -o "%(autonumber)s-%(title)s.%(ext)s" ] number downloaded files starting from 00000
-t, --title [deprecated] use title in file name (default)
-l, --literal [deprecated] alias of --title
-w, --no-overwrites do not overwrite files
-c, --continue force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.
--no-continue do not resume partially downloaded files (restart from beginning)
--no-part do not use .part files - write directly into output file
--no-mtime do not use the Last-modified header to set the file modification time
--write-description write video description to a .description file
--write-info-json write video metadata to a .info.json file
--write-annotations write video annotations to a .annotation file
--load-info FILE json file containing the video information (created with the "--write-json" option)
--cookies FILE file to read cookies from and dump cookie jar in
-A, --auto-number [deprecated; use -o "%(autonumber)s-%(title)s.%(ext)s" ] Number downloaded files starting from 00000
-t, --title [deprecated] Use title in file name (default)
-l, --literal [deprecated] Alias of --title
-w, --no-overwrites Do not overwrite files
-c, --continue Force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.
--no-continue Do not resume partially downloaded files (restart from beginning)
--no-part Do not use .part files - write directly into output file
--no-mtime Do not use the Last-modified header to set the file modification time
--write-description Write video description to a .description file
--write-info-json Write video metadata to a .info.json file
--write-annotations Write video annotations to a .annotation file
--load-info FILE JSON file containing the video information (created with the "--write-info-json" option)
--cookies FILE File to read cookies from and dump cookie jar in
--cache-dir DIR Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl
or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may
change.
@ -142,49 +142,49 @@ which means you can modify it, redistribute it or use it however you like.
--rm-cache-dir Delete all filesystem cache files
## Thumbnail images:
--write-thumbnail write thumbnail image to disk
--write-all-thumbnails write all thumbnail image formats to disk
--write-thumbnail Write thumbnail image to disk
--write-all-thumbnails Write all thumbnail image formats to disk
--list-thumbnails Simulate and list all available thumbnail formats
## Verbosity / Simulation Options:
-q, --quiet activates quiet mode
-q, --quiet Activate quiet mode
--no-warnings Ignore warnings
-s, --simulate do not download the video and do not write anything to disk
--skip-download do not download the video
-g, --get-url simulate, quiet but print URL
-e, --get-title simulate, quiet but print title
--get-id simulate, quiet but print id
--get-thumbnail simulate, quiet but print thumbnail URL
--get-description simulate, quiet but print video description
--get-duration simulate, quiet but print video length
--get-filename simulate, quiet but print output filename
--get-format simulate, quiet but print output format
-j, --dump-json simulate, quiet but print JSON information. See --output for a description of available keys.
-J, --dump-single-json simulate, quiet but print JSON information for each command-line argument. If the URL refers to a playlist, dump the whole playlist
-s, --simulate Do not download the video and do not write anything to disk
--skip-download Do not download the video
-g, --get-url Simulate, quiet but print URL
-e, --get-title Simulate, quiet but print title
--get-id Simulate, quiet but print id
--get-thumbnail Simulate, quiet but print thumbnail URL
--get-description Simulate, quiet but print video description
--get-duration Simulate, quiet but print video length
--get-filename Simulate, quiet but print output filename
--get-format Simulate, quiet but print output format
-j, --dump-json Simulate, quiet but print JSON information. See --output for a description of available keys.
-J, --dump-single-json Simulate, quiet but print JSON information for each command-line argument. If the URL refers to a playlist, dump the whole playlist
information in a single line.
--print-json Be quiet and print the video information as JSON (video is still being downloaded).
--newline output progress bar as new lines
--no-progress do not print progress bar
--console-title display progress in console titlebar
-v, --verbose print various debugging information
--dump-pages print downloaded pages to debug problems (very verbose)
--newline Output progress bar as new lines
--no-progress Do not print progress bar
--console-title Display progress in console titlebar
-v, --verbose Print various debugging information
--dump-pages Print downloaded pages to debug problems (very verbose)
--write-pages Write downloaded intermediary pages to files in the current directory to debug problems
--print-traffic Display sent and read HTTP traffic
-C, --call-home Contact the youtube-dl server for debugging.
--no-call-home Do NOT contact the youtube-dl server for debugging.
-C, --call-home Contact the youtube-dl server for debugging
--no-call-home Do NOT contact the youtube-dl server for debugging
## Workarounds:
--encoding ENCODING Force the specified encoding (experimental)
--no-check-certificate Suppress HTTPS certificate validation.
--no-check-certificate Suppress HTTPS certificate validation
--prefer-insecure Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)
--user-agent UA specify a custom user agent
--referer URL specify a custom referer, use if the video access is restricted to one domain
--add-header FIELD:VALUE specify a custom HTTP header and its value, separated by a colon ':'. You can use this option multiple times
--user-agent UA Specify a custom user agent
--referer URL Specify a custom referer, use if the video access is restricted to one domain
--add-header FIELD:VALUE Specify a custom HTTP header and its value, separated by a colon ':'. You can use this option multiple times
--bidi-workaround Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH
--sleep-interval SECONDS Number of seconds to sleep before each download.
## Video Format Options:
-f, --format FORMAT video format code, specify the order of preference using slashes, as in -f 22/17/18 . Instead of format codes, you can select by
-f, --format FORMAT Video format code, specify the order of preference using slashes, as in -f 22/17/18 . Instead of format codes, you can select by
extension for the extensions aac, m4a, mp3, mp4, ogg, wav, webm. You can also use the special names "best", "bestvideo", "bestaudio",
"worst". You can filter the video results by putting a condition in brackets, as in -f "best[height=720]" (or -f "[filesize>10M]").
This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec,
@ -194,44 +194,44 @@ which means you can modify it, redistribute it or use it however you like.
Use commas to download multiple audio formats, such as -f 136/137/mp4/bestvideo,140/m4a/bestaudio. You can merge the video and audio
of two formats into a single file using -f <video-format>+<audio-format> (requires ffmpeg or avconv), for example -f
bestvideo+bestaudio.
--all-formats download all available video formats
--prefer-free-formats prefer free video formats unless a specific one is requested
--max-quality FORMAT highest quality format to download
-F, --list-formats list all available formats
--all-formats Download all available video formats
--prefer-free-formats Prefer free video formats unless a specific one is requested
--max-quality FORMAT Highest quality format to download
-F, --list-formats List all available formats
--youtube-skip-dash-manifest Do not download the DASH manifest on YouTube videos
--merge-output-format FORMAT If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.Ignored if no
merge is required
## Subtitle Options:
--write-sub write subtitle file
--write-auto-sub write automatic subtitle file (youtube only)
--all-subs downloads all the available subtitles of the video
--list-subs lists all available subtitles for the video
--sub-format FORMAT subtitle format, accepts formats preference, for example: "ass/srt/best"
--sub-lang LANGS languages of the subtitles to download (optional) separated by commas, use IETF language tags like 'en,pt'
--write-sub Write subtitle file
--write-auto-sub Write automatic subtitle file (YouTube only)
--all-subs Download all the available subtitles of the video
--list-subs List all available subtitles for the video
--sub-format FORMAT Subtitle format, accepts formats preference, for example: "srt" or "ass/srt/best"
--sub-lang LANGS Languages of the subtitles to download (optional) separated by commas, use IETF language tags like 'en,pt'
## Authentication Options:
-u, --username USERNAME login with this account ID
-p, --password PASSWORD account password. If this option is left out, youtube-dl will ask interactively.
-2, --twofactor TWOFACTOR two-factor auth code
-n, --netrc use .netrc authentication data
--video-password PASSWORD video password (vimeo, smotri)
-u, --username USERNAME Login with this account ID
-p, --password PASSWORD Account password. If this option is left out, youtube-dl will ask interactively.
-2, --twofactor TWOFACTOR Two-factor auth code
-n, --netrc Use .netrc authentication data
--video-password PASSWORD Video password (vimeo, smotri)
## Post-processing Options:
-x, --extract-audio convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)
--audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
--audio-quality QUALITY ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K
(default 5)
-x, --extract-audio Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)
--audio-format FORMAT Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
--audio-quality QUALITY Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default
5)
--recode-video FORMAT Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)
-k, --keep-video keeps the video file on disk after the post-processing; the video is erased by default
--no-post-overwrites do not overwrite post-processed files; the post-processed files are overwritten by default
--embed-subs embed subtitles in the video (only for mp4 videos)
--embed-thumbnail embed thumbnail in the audio as cover art
--add-metadata write metadata to the video file
--metadata-from-title FORMAT parse additional metadata like song title / artist from the video title. The format syntax is the same as --output, the parsed
-k, --keep-video Keep the video file on disk after the post-processing; the video is erased by default
--no-post-overwrites Do not overwrite post-processed files; the post-processed files are overwritten by default
--embed-subs Embed subtitles in the video (only for mp4 videos)
--embed-thumbnail Embed thumbnail in the audio as cover art
--add-metadata Write metadata to the video file
--metadata-from-title FORMAT Parse additional metadata like song title / artist from the video title. The format syntax is the same as --output, the parsed
parameters replace existing values. Additional templates: %(album), %(artist). Example: --metadata-from-title "%(artist)s -
%(title)s" matches a title like "Coldplay - Paradise"
--xattrs write metadata to the video file's xattrs (using dublin core and xdg standards)
--xattrs Write metadata to the video file's xattrs (using dublin core and xdg standards)
--fixup POLICY Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default;
fix file if we can, warn otherwise)
--prefer-avconv Prefer avconv over ffmpeg for running the postprocessors (default)

5
docs/supportedsites.md
View File

@ -166,6 +166,7 @@
- **Gamekings**
- **GameOne**
- **gameone:playlist**
- **Gamersyde**
- **GameSpot**
- **GameStar**
- **Gametrailers**
@ -351,6 +352,7 @@
- **PornHub**
- **PornHubPlaylist**
- **Pornotube**
- **PornoVoisines**
- **PornoXO**
- **PrimeShareTV**
- **PromptFile**
@ -362,6 +364,7 @@
- **radio.de**
- **radiobremen**
- **radiofrance**
- **RadioJavan**
- **Rai**
- **RBMARadio**
- **RedTube**
@ -422,6 +425,7 @@
- **southpark.cc.com**
- **southpark.de**
- **Space**
- **SpankBang**
- **Spankwire**
- **Spiegel**
- **Spiegel:Article**: Articles on spiegel.de
@ -501,6 +505,7 @@
- **Ubu**
- **udemy**
- **udemy:course**
- **UDNEmbed**
- **Ultimedia**
- **Unistra**
- **Urort**: NRK P3 Urørt

5
test/test_execution.py
View File

@ -8,6 +8,9 @@ import unittest
import sys
import os
import subprocess
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.utils import encodeArgument
rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
@ -31,7 +34,7 @@ class TestExecution(unittest.TestCase):
def test_cmdline_umlauts(self):
p = subprocess.Popen(
[sys.executable, 'youtube_dl/__main__.py', 'ä', '--version'],
[sys.executable, 'youtube_dl/__main__.py', encodeArgument('ä'), '--version'],
cwd=rootDir, stdout=_DEV_NULL, stderr=subprocess.PIPE)
_, stderr = p.communicate()
self.assertFalse(stderr)

7
test/test_utils.py
View File

@ -227,6 +227,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(
unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
'20150202')
self.assertEqual(unified_strdate('25-09-2014'), '20140925')
def test_find_xpath_attr(self):
testxml = '''<root>
@ -470,6 +471,12 @@ class TestUtil(unittest.TestCase):
self.assertEqual(d['x'], 1)
self.assertEqual(d['y'], 'a')
on = js_to_json('["abc", "def",]')
self.assertEqual(json.loads(on), ['abc', 'def'])
on = js_to_json('{"abc": "def",}')
self.assertEqual(json.loads(on), {'abc': 'def'})
def test_clean_html(self):
self.assertEqual(clean_html('a:\nb'), 'a: b')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')

8
youtube_dl/YoutubeDL.py
View File

@ -1768,14 +1768,6 @@ class YoutubeDL(object):
debuglevel = 1 if self.params.get('debug_printtraffic') else 0
https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
# The ssl context is only available in python 2.7.9 and 3.x
if hasattr(https_handler, '_context'):
ctx = https_handler._context
# get_ca_certs is unavailable prior to python 3.4
if hasattr(ctx, 'get_ca_certs') and len(ctx.get_ca_certs()) == 0:
self.report_warning(
'No ssl certificates were loaded, urls that use https '
'won\'t work')
ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
opener = compat_urllib_request.build_opener(
proxy_handler, https_handler, cookie_processor, ydlh)

4
youtube_dl/__init__.py
View File

@ -189,10 +189,6 @@ def _real_main(argv=None):
if opts.allsubtitles and not opts.writeautomaticsub:
opts.writesubtitles = True
if sys.version_info < (3,):
# In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
if opts.outtmpl is not None:
opts.outtmpl = opts.outtmpl.decode(preferredencoding())
outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
(opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
(opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or

6
youtube_dl/extractor/__init__.py
View File

@ -90,6 +90,7 @@ from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .condenast import CondeNastIE
from .cracked import CrackedIE
from .criterion import CriterionIE
from .crooksandliars import CrooksAndLiarsIE
from .crunchyroll import (
CrunchyrollIE,
CrunchyrollShowPlaylistIE
@ -177,6 +178,7 @@ from .gameone import (
GameOneIE,
GameOnePlaylistIE,
)
from .gamersyde import GamersydeIE
from .gamespot import GameSpotIE
from .gamestar import GameStarIE
from .gametrailers import GametrailersIE
@ -387,6 +389,7 @@ from .pornhub import (
PornHubPlaylistIE,
)
from .pornotube import PornotubeIE
from .pornovoisines import PornoVoisinesIE
from .pornoxo import PornoXOIE
from .primesharetv import PrimeShareTVIE
from .promptfile import PromptFileIE
@ -396,6 +399,7 @@ from .pyvideo import PyvideoIE
from .quickvid import QuickVidIE
from .r7 import R7IE
from .radiode import RadioDeIE
from .radiojavan import RadioJavanIE
from .radiobremen import RadioBremenIE
from .radiofrance import RadioFranceIE
from .rai import RaiIE
@ -468,6 +472,7 @@ from .southpark import (
SouthparkDeIE,
)
from .space import SpaceIE
from .spankbang import SpankBangIE
from .spankwire import SpankwireIE
from .spiegel import SpiegelIE, SpiegelArticleIE
from .spiegeltv import SpiegeltvIE
@ -553,6 +558,7 @@ from .udemy import (
UdemyIE,
UdemyCourseIE
)
from .udn import UDNEmbedIE
from .ultimedia import UltimediaIE
from .unistra import UnistraIE
from .urort import UrortIE

15
youtube_dl/extractor/addanime.py
View File

@ -11,12 +11,13 @@ from ..compat import (
)
from ..utils import (
ExtractorError,
qualities,
)
class AddAnimeIE(InfoExtractor):
_VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<id>[\w_]+)(?:.*)'
_TEST = {
_VALID_URL = r'http://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
_TESTS = [{
'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
'md5': '72954ea10bc979ab5e2eb288b21425a0',
'info_dict': {
@ -25,7 +26,10 @@ class AddAnimeIE(InfoExtractor):
'description': 'One Piece 606',
'title': 'One Piece 606',
}
}
}, {
'url': 'http://add-anime.net/video/MDUGWYKNGBD8/One-Piece-687',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@ -63,8 +67,10 @@ class AddAnimeIE(InfoExtractor):
note='Confirming after redirect')
webpage = self._download_webpage(url, video_id)
FORMATS = ('normal', 'hq')
quality = qualities(FORMATS)
formats = []
for format_id in ('normal', 'hq'):
for format_id in FORMATS:
rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)
video_url = self._search_regex(rex, webpage, 'video file URLx',
fatal=False)
@ -73,6 +79,7 @@ class AddAnimeIE(InfoExtractor):
formats.append({
'format_id': format_id,
'url': video_url,
'quality': quality(format_id),
})
self._sort_formats(formats)
video_title = self._og_search_title(webpage)

19
youtube_dl/extractor/aftonbladet.py
View File

@ -2,10 +2,11 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import int_or_none
class AftonbladetIE(InfoExtractor):
_VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+?(?P<video_id>article[0-9]+)\.ab(?:$|[?#])'
_VALID_URL = r'http://tv\.aftonbladet\.se/webbtv.+?(?P<id>article[0-9]+)\.ab(?:$|[?#])'
_TEST = {
'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab',
'info_dict': {
@ -43,9 +44,9 @@ class AftonbladetIE(InfoExtractor):
formats.append({
'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
'ext': 'mp4',
'width': fmt['width'],
'height': fmt['height'],
'tbr': fmt['bitrate'],
'width': int_or_none(fmt.get('width')),
'height': int_or_none(fmt.get('height')),
'tbr': int_or_none(fmt.get('bitrate')),
'protocol': 'http',
})
self._sort_formats(formats)
@ -54,9 +55,9 @@ class AftonbladetIE(InfoExtractor):
'id': video_id,
'title': internal_meta_json['title'],
'formats': formats,
'thumbnail': internal_meta_json['imageUrl'],
'description': internal_meta_json['shortPreamble'],
'timestamp': internal_meta_json['timePublished'],
'duration': internal_meta_json['duration'],
'view_count': internal_meta_json['views'],
'thumbnail': internal_meta_json.get('imageUrl'),
'description': internal_meta_json.get('shortPreamble'),
'timestamp': int_or_none(internal_meta_json.get('timePublished')),
'duration': int_or_none(internal_meta_json.get('duration')),
'view_count': int_or_none(internal_meta_json.get('views')),
}

1
youtube_dl/extractor/bliptv.py
View File

@ -172,6 +172,7 @@ class BlipTVIE(InfoExtractor):
'width': int_or_none(media_content.get('width')),
'height': int_or_none(media_content.get('height')),
})
self._check_formats(formats, video_id)
self._sort_formats(formats)
subtitles = self.extract_subtitles(video_id, subtitles_urls)

25
youtube_dl/extractor/bloomberg.py
View File

@ -6,32 +6,39 @@ from .common import InfoExtractor
class BloombergIE(InfoExtractor):
_VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<id>.+?)\.html'
_VALID_URL = r'https?://www\.bloomberg\.com/news/videos/[^/]+/(?P<id>[^/?#]+)'
_TEST = {
'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2',
# The md5 checksum changes
'info_dict': {
'id': 'qurhIVlJSB6hzkVi229d8g',
'ext': 'flv',
'title': 'Shah\'s Presentation on Foreign-Exchange Strategies',
'description': 'md5:0681e0d30dcdfc6abf34594961d8ea88',
'description': 'md5:a8ba0302912d03d246979735c17d2761',
},
}
def _real_extract(self, url):
name = self._match_id(url)
webpage = self._download_webpage(url, name)
f4m_url = self._search_regex(
r'<source src="(https?://[^"]+\.f4m.*?)"', webpage,
'f4m url')
video_id = self._search_regex(r'"bmmrId":"(.+?)"', webpage, 'id')
title = re.sub(': Video$', '', self._og_search_title(webpage))
embed_info = self._download_json(
'http://www.bloomberg.com/api/embed?id=%s' % video_id, video_id)
formats = []
for stream in embed_info['streams']:
if stream["muxing_format"] == "TS":
formats.extend(self._extract_m3u8_formats(stream['url'], video_id))
else:
formats.extend(self._extract_f4m_formats(stream['url'], video_id))
self._sort_formats(formats)
return {
'id': name.split('-')[-1],
'id': video_id,
'title': title,
'formats': self._extract_f4m_formats(f4m_url, name),
'formats': formats,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}

5
youtube_dl/extractor/cnn.py
View File

@ -12,7 +12,7 @@ from ..utils import (
class CNNIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/
(?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:cnn|hln|ktvk)(?:-ap)?|(?=&)))'''
(?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z]{3,5})(?:-ap)?|(?=&)))'''
_TESTS = [{
'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
@ -48,6 +48,9 @@ class CNNIE(InfoExtractor):
}, {
'url': 'http://cnn.com/video/?/video/politics/2015/03/27/pkg-arizona-senator-church-attendance-mandatory.ktvk',
'only_matching': True,
}, {
'url': 'http://cnn.com/video/?/video/us/2015/04/06/dnt-baker-refuses-anti-gay-order.wkmg',
'only_matching': True,
}]
def _real_extract(self, url):

2
youtube_dl/extractor/common.py
View File

@ -822,7 +822,7 @@ class InfoExtractor(object):
(media_el.attrib.get('href') or media_el.attrib.get('url')))
tbr = int_or_none(media_el.attrib.get('bitrate'))
formats.append({
'format_id': '-'.join(filter(None, [f4m_id, 'f4m-%d' % (i if tbr is None else tbr)])),
'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])),
'url': manifest_url,
'ext': 'flv',
'tbr': tbr,

60
youtube_dl/extractor/crooksandliars.py Normal file
View File

@ -0,0 +1,60 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
qualities,
)
class CrooksAndLiarsIE(InfoExtractor):
_VALID_URL = r'https?://embed\.crooksandliars\.com/(?:embed|v)/(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'https://embed.crooksandliars.com/embed/8RUoRhRi',
'info_dict': {
'id': '8RUoRhRi',
'ext': 'mp4',
'title': 'Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!',
'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
'thumbnail': 're:^https?://.*\.jpg',
'timestamp': 1428207000,
'upload_date': '20150405',
'uploader': 'Heather',
'duration': 236,
}
}, {
'url': 'http://embed.crooksandliars.com/v/MTE3MjUtMzQ2MzA',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://embed.crooksandliars.com/embed/%s' % video_id, video_id)
manifest = self._parse_json(
self._search_regex(
r'var\s+manifest\s*=\s*({.+?})\n', webpage, 'manifest JSON'),
video_id)
quality = qualities(('webm_low', 'mp4_low', 'webm_high', 'mp4_high'))
formats = [{
'url': item['url'],
'format_id': item['type'],
'quality': quality(item['type']),
} for item in manifest['flavors'] if item['mime'].startswith('video/')]
self._sort_formats(formats)
return {
'url': url,
'id': video_id,
'title': manifest['title'],
'description': manifest.get('description'),
'thumbnail': self._proto_relative_url(manifest.get('poster')),
'timestamp': int_or_none(manifest.get('created')),
'uploader': manifest.get('author'),
'duration': int_or_none(manifest.get('duration')),
'formats': formats,
}

2
youtube_dl/extractor/dailymotion.py
View File

@ -224,7 +224,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
class DailymotionUserIE(DailymotionPlaylistIE):
IE_NAME = 'dailymotion:user'
_VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
_VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?:old/)?user/(?P<user>[^/]+)'
_PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
_TESTS = [{
'url': 'https://www.dailymotion.com/user/nqtv',

26
youtube_dl/extractor/dreisat.py
View File

@ -3,22 +3,25 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import unified_strdate
from ..utils import (
ExtractorError,
unified_strdate,
)
class DreiSatIE(InfoExtractor):
IE_NAME = '3sat'
_VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
_TEST = {
'url': 'http://www.3sat.de/mediathek/index.php?obj=36983',
'md5': '9dcfe344732808dbfcc901537973c922',
'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
'md5': 'be37228896d30a88f315b638900a026e',
'info_dict': {
'id': '36983',
'id': '45918',
'ext': 'mp4',
'title': 'Kaffeeland Schweiz',
'description': 'md5:cc4424b18b75ae9948b13929a0814033',
'title': 'Waidmannsheil',
'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
'uploader': '3sat',
'upload_date': '20130622'
'upload_date': '20140913'
}
}
@ -28,6 +31,15 @@ class DreiSatIE(InfoExtractor):
details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
details_doc = self._download_xml(details_url, video_id, 'Downloading video details')
status_code = details_doc.find('./status/statuscode')
if status_code is not None and status_code.text != 'ok':
code = status_code.text
if code == 'notVisibleAnymore':
message = 'Video %s is not available' % video_id
else:
message = '%s returned error: %s' % (self.IE_NAME, code)
raise ExtractorError(message, expected=True)
thumbnail_els = details_doc.findall('.//teaserimage')
thumbnails = [{
'width': int(te.attrib['key'].partition('x')[0]),

21
youtube_dl/extractor/drtv.py
View File

@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor, ExtractorError
@ -8,16 +9,16 @@ class DRTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_TEST = {
'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8',
'md5': '4a7e1dd65cdb2643500a3f753c942f25',
'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
'info_dict': {
'id': 'partiets-mand-7-8',
'id': 'panisk-paske-5',
'ext': 'mp4',
'title': 'Partiets mand (7:8)',
'description': 'md5:a684b90a8f9336cd4aab94b7647d7862',
'timestamp': 1403047940,
'upload_date': '20140617',
'duration': 1299.040,
'title': 'Panisk Påske (5)',
'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c',
'timestamp': 1426984612,
'upload_date': '20150322',
'duration': 1455,
},
}
@ -26,6 +27,10 @@ class DRTVIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
if '>Programmet er ikke længere tilgængeligt' in webpage:
raise ExtractorError(
'Video %s is not available' % video_id, expected=True)
video_id = self._search_regex(
r'data-(?:material-identifier|episode-slug)="([^"]+)"',
webpage, 'video id')

6
youtube_dl/extractor/dump.py
View File

@ -28,12 +28,12 @@ class DumpIE(InfoExtractor):
video_url = self._search_regex(
r's1.addVariable\("file",\s*"([^"]+)"', webpage, 'video URL')
thumb = self._og_search_thumbnail(webpage)
title = self._search_regex(r'<b>([^"]+)</b>', webpage, 'title')
title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
return {
'id': video_id,
'title': title,
'url': video_url,
'thumbnail': thumb,
'thumbnail': thumbnail,
}

6
youtube_dl/extractor/dumpert.py
View File

@ -4,6 +4,7 @@ from __future__ import unicode_literals
import base64
from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import qualities
@ -23,7 +24,10 @@ class DumpertIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'nsfw=1')
webpage = self._download_webpage(req, video_id)
files_base64 = self._search_regex(
r'data-files="([^"]+)"', webpage, 'data files')

1
youtube_dl/extractor/eagleplatform.py
View File

@ -45,6 +45,7 @@ class EaglePlatformIE(InfoExtractor):
'duration': 216,
'view_count': int,
},
'skip': 'Georestricted',
}]
def _handle_error(self, response):

19
youtube_dl/extractor/ellentv.py
View File

@ -13,15 +13,15 @@ from ..utils import (
class EllenTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
_TESTS = [{
'url': 'http://www.ellentv.com/videos/0-7jqrsr18/',
'md5': 'e4af06f3bf0d5f471921a18db5764642',
'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
'md5': '8e3c576bf2e9bfff4d76565f56f94c9c',
'info_dict': {
'id': '0-7jqrsr18',
'id': '0-ipq1gsai',
'ext': 'mp4',
'title': 'What\'s Wrong with These Photos? A Whole Lot',
'description': 'md5:35f152dc66b587cf13e6d2cf4fa467f6',
'timestamp': 1406876400,
'upload_date': '20140801',
'title': 'Fast Fingers of Fate',
'description': 'md5:686114ced0a032926935e9015ee794ac',
'timestamp': 1428033600,
'upload_date': '20150403',
}
}, {
'url': 'http://ellentube.com/videos/0-dvzmabd5/',
@ -40,14 +40,15 @@ class EllenTVIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_meta('VideoURL', webpage, 'url')
video_url = self._html_search_meta('VideoURL', webpage, 'url', fatal=True)
title = self._og_search_title(webpage, default=None) or self._search_regex(
r'pageName\s*=\s*"([^"]+)"', webpage, 'title')
description = self._html_search_meta(
'description', webpage, 'description') or self._og_search_description(webpage)
timestamp = parse_iso8601(self._search_regex(
r'<span class="publish-date"><time datetime="([^"]+)">',
webpage, 'timestamp'))
webpage, 'timestamp', fatal=False))
return {
'id': video_id,

36
youtube_dl/extractor/francetv.py
View File

@ -14,7 +14,9 @@ from ..utils import (
clean_html,
ExtractorError,
int_or_none,
float_or_none,
parse_duration,
determine_ext,
)
@ -50,7 +52,8 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
if not video_url:
continue
format_id = video['format']
if video_url.endswith('.f4m'):
ext = determine_ext(video_url)
if ext == 'f4m':
if georestricted:
# See https://github.com/rg3/youtube-dl/issues/3963
# m3u8 urls work fine
@ -60,12 +63,9 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path,
video_id, 'Downloading f4m manifest token', fatal=False)
if f4m_url:
f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
for f4m_format in f4m_formats:
f4m_format['preference'] = 1
formats.extend(f4m_formats)
elif video_url.endswith('.m3u8'):
formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4'))
formats.extend(self._extract_f4m_formats(f4m_url, video_id, 1, format_id))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4', m3u8_id=format_id))
elif video_url.startswith('rtmp'):
formats.append({
'url': video_url,
@ -86,7 +86,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
'title': info['titre'],
'description': clean_html(info['synopsis']),
'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
'duration': parse_duration(info['duree']),
'duration': float_or_none(info.get('real_duration'), 1000) or parse_duration(info['duree']),
'timestamp': int_or_none(info['diffusion']['timestamp']),
'formats': formats,
}
@ -260,22 +260,28 @@ class CultureboxIE(FranceTVBaseInfoExtractor):
_VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
_TEST = {
'url': 'http://culturebox.francetvinfo.fr/festivals/dans-les-jardins-de-william-christie/dans-les-jardins-de-william-christie-le-camus-162553',
'md5': '5ad6dec1ffb2a3fbcb20cc4b744be8d6',
'url': 'http://culturebox.francetvinfo.fr/live/musique/musique-classique/le-livre-vermeil-de-montserrat-a-la-cathedrale-delne-214511',
'md5': '9b88dc156781c4dbebd4c3e066e0b1d6',
'info_dict': {
'id': 'EV_22853',
'id': 'EV_50111',
'ext': 'flv',
'title': 'Dans les jardins de William Christie - Le Camus',
'description': 'md5:4710c82315c40f0c865ca8b9a68b5299',
'upload_date': '20140829',
'timestamp': 1409317200,
'title': "Le Livre Vermeil de Montserrat à la Cathédrale d'Elne",
'description': 'md5:f8a4ad202e8fe533e2c493cc12e739d9',
'upload_date': '20150320',
'timestamp': 1426892400,
'duration': 2760.9,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name = mobj.group('name')
webpage = self._download_webpage(url, name)
if ">Ce live n'est plus disponible en replay<" in webpage:
raise ExtractorError('Video %s is not available' % name, expected=True)
video_id, catalogue = self._search_regex(
r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')

70
youtube_dl/extractor/gamersyde.py Normal file
View File

@ -0,0 +1,70 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
js_to_json,
parse_duration,
remove_start,
)
class GamersydeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gamersyde\.com/hqstream_(?P<display_id>[\da-z_]+)-(?P<id>\d+)_[a-z]{2}\.html'
_TEST = {
'url': 'http://www.gamersyde.com/hqstream_bloodborne_birth_of_a_hero-34371_en.html',
'md5': 'f38d400d32f19724570040d5ce3a505f',
'info_dict': {
'id': '34371',
'ext': 'mp4',
'duration': 372,
'title': 'Bloodborne - Birth of a hero',
'thumbnail': 're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
playlist = self._parse_json(
self._search_regex(
r'(?s)playlist: \[({.+?})\]\s*}\);', webpage, 'files'),
display_id, transform_source=js_to_json)
formats = []
for source in playlist['sources']:
video_url = source.get('file')
if not video_url:
continue
format_id = source.get('label')
f = {
'url': video_url,
'format_id': format_id,
}
m = re.search(r'^(?P<height>\d+)[pP](?P<fps>\d+)fps', format_id)
if m:
f.update({
'height': int(m.group('height')),
'fps': int(m.group('fps')),
})
formats.append(f)
self._sort_formats(formats)
title = remove_start(playlist['title'], '%s - ' % video_id)
thumbnail = playlist.get('image')
duration = parse_duration(self._search_regex(
r'Length:</label>([^<]+)<', webpage, 'duration', fatal=False))
return {
'id': video_id,
'display_id': display_id,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
}

51
youtube_dl/extractor/generic.py
View File

@ -34,6 +34,7 @@ from .ooyala import OoyalaIE
from .rutv import RUTVIE
from .smotri import SmotriIE
from .condenast import CondeNastIE
from .udn import UDNEmbedIE
class GenericIE(InfoExtractor):
@ -641,6 +642,32 @@ class GenericIE(InfoExtractor):
'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
}
},
# Crooks and Liars embed
{
'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
'info_dict': {
'id': '8RUoRhRi',
'ext': 'mp4',
'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
'timestamp': 1428207000,
'upload_date': '20150405',
'uploader': 'Heather',
},
},
# Crooks and Liars external embed
{
'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
'info_dict': {
'id': 'MTE3MjUtMzQ2MzA',
'ext': 'mp4',
'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
'timestamp': 1265032391,
'upload_date': '20100201',
'uploader': 'Heather',
},
},
# NBC Sports vplayer embed
{
'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
@ -650,6 +677,17 @@ class GenericIE(InfoExtractor):
'title': "PFT Live: New leader in the 'new-look' defense",
'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
},
},
# UDN embed
{
'url': 'http://www.udn.com/news/story/7314/822787',
'md5': 'de06b4c90b042c128395a88f0384817e',
'info_dict': {
'id': '300040',
'ext': 'mp4',
'title': '生物老師男變女 全校挺"做自己"',
'thumbnail': 're:^https?://.*\.jpg$',
}
}
]
@ -1263,11 +1301,24 @@ class GenericIE(InfoExtractor):
if mobj is not None:
return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
# Look for Crooks and Liars embeds
mobj = re.search(
r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for NBC Sports VPlayer embeds
nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
if nbc_sports_url:
return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
# Look for UDN embeds
mobj = re.search(
r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
if mobj is not None:
return self.url_result(
compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
def check_video(vurl):
if YoutubeIE.suitable(vurl):
return True

24
youtube_dl/extractor/hitbox.py
View File

@ -10,6 +10,7 @@ from ..utils import (
float_or_none,
int_or_none,
compat_str,
determine_ext,
)
@ -147,12 +148,27 @@ class HitboxLiveIE(HitboxIE):
servers.append(base_url)
for stream in cdn.get('bitrates'):
label = stream.get('label')
if label != 'Auto':
if label == 'Auto':
continue
stream_url = stream.get('url')
if not stream_url:
continue
bitrate = int_or_none(stream.get('bitrate'))
if stream.get('provider') == 'hls' or determine_ext(stream_url) == 'm3u8':
if not stream_url.startswith('http'):
continue
formats.append({
'url': '%s/%s' % (base_url, stream.get('url')),
'url': stream_url,
'ext': 'mp4',
'vbr': stream.get('bitrate'),
'resolution': label,
'tbr': bitrate,
'format_note': label,
'rtmp_live': True,
})
else:
formats.append({
'url': '%s/%s' % (base_url, stream_url),
'ext': 'mp4',
'tbr': bitrate,
'rtmp_live': True,
'format_note': host,
'page_url': url,

5
youtube_dl/extractor/livestream.py
View File

@ -21,7 +21,7 @@ from ..utils import (
class LivestreamIE(InfoExtractor):
IE_NAME = 'livestream'
_VALID_URL = r'https?://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>[0-9]+)(?:/player)?)?/?(?:$|[?#])'
_VALID_URL = r'https?://(?:new\.)?livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>[0-9]+)(?:/player)?)?/?(?:$|[?#])'
_TESTS = [{
'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
'md5': '53274c76ba7754fb0e8d072716f2292b',
@ -51,6 +51,9 @@ class LivestreamIE(InfoExtractor):
}, {
'url': 'https://new.livestream.com/accounts/362/events/3557232/videos/67864563/player?autoPlay=false&height=360&mute=false&width=640',
'only_matching': True,
}, {
'url': 'http://livestream.com/bsww/concacafbeachsoccercampeonato2015',
'only_matching': True,
}]
def _parse_smil(self, video_id, smil_url):

2
youtube_dl/extractor/mixcloud.py
View File

@ -97,7 +97,7 @@ class MixcloudIE(InfoExtractor):
r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
description = self._og_search_description(webpage)
like_count = str_to_int(self._search_regex(
r'\bbutton-favorite\b.+m-ajax-toggle-count="([^"]+)"',
r'\bbutton-favorite\b[^>]+m-ajax-toggle-count="([^"]+)"',
webpage, 'like count', fatal=False))
view_count = str_to_int(self._search_regex(
[r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',

96
youtube_dl/extractor/pornovoisines.py Normal file
View File

@ -0,0 +1,96 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import random
from .common import InfoExtractor
from ..utils import (
int_or_none,
float_or_none,
unified_strdate,
)
class PornoVoisinesIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?pornovoisines\.com/showvideo/(?P<id>\d+)/(?P<display_id>[^/]+)'
_VIDEO_URL_TEMPLATE = 'http://stream%d.pornovoisines.com' \
'/static/media/video/transcoded/%s-640x360-1000-trscded.mp4'
_SERVER_NUMBERS = (1, 2)
_TEST = {
'url': 'http://www.pornovoisines.com/showvideo/1285/recherche-appartement/',
'md5': '5ac670803bc12e9e7f9f662ce64cf1d1',
'info_dict': {
'id': '1285',
'display_id': 'recherche-appartement',
'ext': 'mp4',
'title': 'Recherche appartement',
'description': 'md5:819ea0b785e2a04667a1a01cdc89594e',
'thumbnail': 're:^https?://.*\.jpg$',
'upload_date': '20140925',
'duration': 120,
'view_count': int,
'average_rating': float,
'categories': ['Débutante', 'Scénario', 'Sodomie'],
'age_limit': 18,
}
}
@classmethod
def build_video_url(cls, num):
return cls._VIDEO_URL_TEMPLATE % (random.choice(cls._SERVER_NUMBERS), num)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, video_id)
video_url = self.build_video_url(video_id)
title = self._html_search_regex(
r'<h1>(.+?)</h1>', webpage, 'title', flags=re.DOTALL)
description = self._html_search_regex(
r'<article id="descriptif">(.+?)</article>',
webpage, "description", fatal=False, flags=re.DOTALL)
thumbnail = self._search_regex(
r'<div id="mediaspace%s">\s*<img src="/?([^"]+)"' % video_id,
webpage, 'thumbnail', fatal=False)
if thumbnail:
thumbnail = 'http://www.pornovoisines.com/%s' % thumbnail
upload_date = unified_strdate(self._search_regex(
r'Publié le ([\d-]+)', webpage, 'upload date', fatal=False))
duration = int_or_none(self._search_regex(
'Durée (\d+)', webpage, 'duration', fatal=False))
view_count = int_or_none(self._search_regex(
r'(\d+) vues', webpage, 'view count', fatal=False))
average_rating = self._search_regex(
r'Note : (\d+,\d+)', webpage, 'average rating', fatal=False)
if average_rating:
average_rating = float_or_none(average_rating.replace(',', '.'))
categories = self._html_search_meta(
'keywords', webpage, 'categories', fatal=False)
if categories:
categories = [category.strip() for category in categories.split(',')]
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
'duration': duration,
'view_count': view_count,
'average_rating': average_rating,
'categories': categories,
'age_limit': 18,
}

6
youtube_dl/extractor/prosiebensat1.py
View File

@ -10,6 +10,7 @@ from ..compat import (
)
from ..utils import (
unified_strdate,
int_or_none,
)
@ -24,7 +25,7 @@ class ProSiebenSat1IE(InfoExtractor):
'info_dict': {
'id': '2104602',
'ext': 'mp4',
'title': 'Staffel 2, Episode 18 - Jahresrückblick',
'title': 'Episode 18 - Staffel 2',
'description': 'md5:8733c81b702ea472e069bc48bb658fc1',
'upload_date': '20131231',
'duration': 5845.04,
@ -266,6 +267,9 @@ class ProSiebenSat1IE(InfoExtractor):
urls_sources = urls_sources.values()
def fix_bitrate(bitrate):
bitrate = int_or_none(bitrate)
if not bitrate:
return None
return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate
for source in urls_sources:

67
youtube_dl/extractor/radiojavan.py Normal file
View File

@ -0,0 +1,67 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import(
unified_strdate,
str_to_int,
)
class RadioJavanIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
_TEST = {
'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',
'md5': 'e85208ffa3ca8b83534fca9fe19af95b',
'info_dict': {
'id': 'chaartaar-ashoobam',
'ext': 'mp4',
'title': 'Chaartaar - Ashoobam',
'thumbnail': 're:^https?://.*\.jpe?g$',
'upload_date': '20150215',
'view_count': int,
'like_count': int,
'dislike_count': int,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
formats = [{
'url': 'https://media.rdjavan.com/media/music_video/%s' % video_path,
'format_id': '%sp' % height,
'height': int(height),
} for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)]
self._sort_formats(formats)
title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._search_regex(
r'class="date_added">Date added: ([^<]+)<',
webpage, 'upload date', fatal=False))
view_count = str_to_int(self._search_regex(
r'class="views">Plays: ([\d,]+)',
webpage, 'view count', fatal=False))
like_count = str_to_int(self._search_regex(
r'class="rating">([\d,]+) likes',
webpage, 'like count', fatal=False))
dislike_count = str_to_int(self._search_regex(
r'class="rating">([\d,]+) dislikes',
webpage, 'dislike count', fatal=False))
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'upload_date': upload_date,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'formats': formats,
}

77
youtube_dl/extractor/rai.py
View File

@ -13,7 +13,7 @@ from ..utils import (
class RaiIE(InfoExtractor):
_VALID_URL = r'(?P<url>http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html)'
_VALID_URL = r'(?P<url>(?P<host>http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it))/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html)'
_TESTS = [
{
'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
@ -62,34 +62,78 @@ class RaiIE(InfoExtractor):
'description': 'Edizione delle ore 20:30 ',
}
},
{
'url': 'http://www.ilcandidato.rai.it/dl/ray/media/Il-Candidato---Primo-episodio-Le-Primarie-28e5525a-b495-45e8-a7c3-bc48ba45d2b6.html',
'md5': '02b64456f7cc09f96ff14e7dd489017e',
'info_dict': {
'id': '28e5525a-b495-45e8-a7c3-bc48ba45d2b6',
'ext': 'flv',
'title': 'Il Candidato - Primo episodio: "Le Primarie"',
'description': 'Primo appuntamento con "Il candidato" con Filippo Timi, alias Piero Zucca presidente!',
'uploader': 'RaiTre',
}
}
]
def _extract_relinker_url(self, webpage):
return self._proto_relative_url(self._search_regex(
[r'name="videourl" content="([^"]+)"', r'var\s+videoURL(?:_MP4)?\s*=\s*"([^"]+)"'],
webpage, 'relinker url', default=None))
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
host = mobj.group('host')
media = self._download_json('%s?json' % mobj.group('url'), video_id, 'Downloading video JSON')
webpage = self._download_webpage(url, video_id)
relinker_url = self._extract_relinker_url(webpage)
if not relinker_url:
iframe_path = self._search_regex(
r'<iframe[^>]+src="/?(dl/[^"]+\?iframe\b[^"]*)"',
webpage, 'iframe')
webpage = self._download_webpage(
'%s/%s' % (host, iframe_path), video_id)
relinker_url = self._extract_relinker_url(webpage)
relinker = self._download_json(
'%s&output=47' % relinker_url, video_id)
media_url = relinker['video'][0]
ct = relinker.get('ct')
if ct == 'f4m':
formats = self._extract_f4m_formats(
media_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id)
else:
formats = [{
'url': media_url,
'format_id': ct,
}]
json_link = self._html_search_meta(
'jsonlink', webpage, 'JSON link', default=None)
if json_link:
media = self._download_json(
host + json_link, video_id, 'Downloading video JSON')
title = media.get('name')
description = media.get('desc')
thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
duration = parse_duration(media.get('length'))
uploader = media.get('author')
upload_date = unified_strdate(media.get('date'))
else:
title = (self._search_regex(
r'var\s+videoTitolo\s*=\s*"(.+?)";',
webpage, 'title', default=None) or self._og_search_title(webpage)).replace('\\"', '"')
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
duration = None
uploader = self._html_search_meta('Editore', webpage, 'uploader')
upload_date = unified_strdate(self._html_search_meta(
'item-date', webpage, 'upload date', default=None))
formats = []
for format_id in ['wmv', 'm3u8', 'mediaUri', 'h264']:
media_url = media.get(format_id)
if not media_url:
continue
formats.append({
'url': media_url,
'format_id': format_id,
'ext': 'mp4',
})
subtitles = self.extract_subtitles(video_id, url)
subtitles = self.extract_subtitles(video_id, webpage)
return {
'id': video_id,
@ -103,8 +147,7 @@ class RaiIE(InfoExtractor):
'subtitles': subtitles,
}
def _get_subtitles(self, video_id, url):
webpage = self._download_webpage(url, video_id)
def _get_subtitles(self, video_id, webpage):
subtitles = {}
m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
if m:

13
youtube_dl/extractor/rtve.py
View File

@ -8,8 +8,10 @@ import time
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
ExtractorError,
float_or_none,
remove_end,
std_headers,
struct_unpack,
)
@ -84,13 +86,22 @@ class RTVEALaCartaIE(InfoExtractor):
'only_matching': True,
}]
def _real_initialize(self):
user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
manager_info = self._download_json(
'http://www.rtve.es/odin/loki/' + user_agent_b64,
None, 'Fetching manager info')
self._manager = manager_info['manager']
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
info = self._download_json(
'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
video_id)['page']['items'][0]
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id
if info['state'] == 'DESPU':
raise ExtractorError('The video is no longer available', expected=True)
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
png = self._download_webpage(png_url, video_id, 'Downloading url information')
video_url = _decrypt_url(png)
if not video_url.endswith('.f4m'):

60
youtube_dl/extractor/spankbang.py Normal file
View File

@ -0,0 +1,60 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class SpankBangIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
_TEST = {
'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
'md5': '1cc433e1d6aa14bc376535b8679302f7',
'info_dict': {
'id': '3vvn',
'ext': 'mp4',
'title': 'fantasy solo',
'description': 'dillion harper masturbates on a bed',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'silly2587',
'age_limit': 18,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
stream_key = self._html_search_regex(
r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
webpage, 'stream key')
formats = [{
'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height),
'ext': 'mp4',
'format_id': '%sp' % height,
'height': int(height),
} for height in re.findall(r'<span[^>]+q_(\d+)p', webpage)]
self._sort_formats(formats)
title = self._html_search_regex(
r'(?s)<h1>(.+?)</h1>', webpage, 'title')
description = self._search_regex(
r'class="desc"[^>]*>([^<]+)',
webpage, 'description', default=None)
thumbnail = self._og_search_thumbnail(webpage)
uploader = self._search_regex(
r'class="user"[^>]*>([^<]+)',
webpage, 'uploader', fatal=False)
age_limit = self._rta_search(webpage)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'formats': formats,
'age_limit': age_limit,
}

24
youtube_dl/extractor/teamcoco.py
View File

@ -4,7 +4,10 @@ import base64
import re
from .common import InfoExtractor
from ..utils import qualities
from ..utils import (
ExtractorError,
qualities,
)
class TeamcocoIE(InfoExtractor):
@ -18,6 +21,7 @@ class TeamcocoIE(InfoExtractor):
'ext': 'mp4',
'title': 'Conan Becomes A Mary Kay Beauty Consultant',
'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.',
'duration': 504,
'age_limit': 0,
}
}, {
@ -28,6 +32,7 @@ class TeamcocoIE(InfoExtractor):
'ext': 'mp4',
'description': 'Louis C.K. got starstruck by George W. Bush, so what? Part one.',
'title': 'Louis C.K. Interview Pt. 1 11/3/11',
'duration': 288,
'age_limit': 0,
}
}
@ -49,18 +54,20 @@ class TeamcocoIE(InfoExtractor):
video_id = self._html_search_regex(
self._VIDEO_ID_REGEXES, webpage, 'video id')
embed_url = 'http://teamcoco.com/embed/v/%s' % video_id
embed = self._download_webpage(
embed_url, video_id, 'Downloading embed page')
player_data = self._parse_json(self._search_regex(
r'Y\.Ginger\.Module\.Player(?:;var\s*player\s*=\s*new\s*m)?\((\{.*?\})\);', embed, 'player data'), video_id)
preloads = re.findall(r'"preload":\s*"([^"]+)"', webpage)
if not preloads:
raise ExtractorError('Preload information could not be extracted')
preload = max([(len(p), p) for p in preloads])[1]
data = self._parse_json(
base64.b64decode(player_data['preload'].encode('ascii')).decode('utf-8'), video_id)
base64.b64decode(preload.encode('ascii')).decode('utf-8'), video_id)
formats = []
get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
for filed in data['files']:
if filed['type'] == 'hls':
formats.extend(self._extract_m3u8_formats(
filed['url'], video_id, ext='mp4'))
else:
m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
if m_format is not None:
format_id = m_format.group(1)
@ -88,5 +95,6 @@ class TeamcocoIE(InfoExtractor):
'title': data['title'],
'thumbnail': data.get('thumb', {}).get('href'),
'description': data.get('teaser'),
'duration': data.get('duration'),
'age_limit': self._family_friendly_search(webpage),
}

49
youtube_dl/extractor/ted.py
View File

@ -5,9 +5,8 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_str,
)
from ..compat import compat_str
from ..utils import int_or_none
class TEDIE(InfoExtractor):
@ -170,17 +169,41 @@ class TEDIE(InfoExtractor):
finfo = self._NATIVE_FORMATS.get(f['format_id'])
if finfo:
f.update(finfo)
else:
# Use rtmp downloads
formats = [{
'format_id': f['name'],
'url': talk_info['streamer'],
'play_path': f['file'],
for format_id, resources in talk_info['resources'].items():
if format_id == 'h264':
for resource in resources:
bitrate = int_or_none(resource.get('bitrate'))
formats.append({
'url': resource['file'],
'format_id': '%s-%sk' % (format_id, bitrate),
'tbr': bitrate,
})
elif format_id == 'rtmp':
streamer = talk_info.get('streamer')
if not streamer:
continue
for resource in resources:
formats.append({
'format_id': '%s-%s' % (format_id, resource.get('name')),
'url': streamer,
'play_path': resource['file'],
'ext': 'flv',
'width': f['width'],
'height': f['height'],
'tbr': f['bitrate'],
} for f in talk_info['resources']['rtmp']]
'width': int_or_none(resource.get('width')),
'height': int_or_none(resource.get('height')),
'tbr': int_or_none(resource.get('bitrate')),
})
elif format_id == 'hls':
formats.extend(self._extract_m3u8_formats(
resources.get('stream'), video_name, 'mp4', m3u8_id=format_id))
audio_download = talk_info.get('audioDownload')
if audio_download:
formats.append({
'url': audio_download,
'format_id': 'audio',
})
self._sort_formats(formats)
video_id = compat_str(talk_info['id'])

34
youtube_dl/extractor/theplatform.py
View File

@ -17,6 +17,7 @@ from ..utils import (
ExtractorError,
xpath_with_ns,
unsmuggle_url,
int_or_none,
)
_x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language'})
@ -28,7 +29,7 @@ class ThePlatformIE(InfoExtractor):
(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/)?
|theplatform:)(?P<id>[^/\?&]+)'''
_TEST = {
_TESTS = [{
# from http://www.metacafe.com/watch/cb-e9I_cZgTgIPd/blackberrys_big_bold_z30/
'url': 'http://link.theplatform.com/s/dJ5BDC/e9I_cZgTgIPd/meta.smil?format=smil&Tracking=true&mbr=true',
'info_dict': {
@ -42,7 +43,20 @@ class ThePlatformIE(InfoExtractor):
# rtmp download
'skip_download': True,
},
}, {
# from http://www.cnet.com/videos/tesla-model-s-a-second-step-towards-a-cleaner-motoring-future/
'url': 'http://link.theplatform.com/s/kYEXFC/22d_qsQ6MIRT',
'info_dict': {
'id': '22d_qsQ6MIRT',
'ext': 'flv',
'description': 'md5:ac330c9258c04f9d7512cf26b9595409',
'title': 'Tesla Model S: A second step towards a cleaner motoring future',
},
'params': {
# rtmp download
'skip_download': True,
}
}]
@staticmethod
def _sign_url(url, sig_key, sig_secret, life=600, include_qs=False):
@ -115,7 +129,7 @@ class ThePlatformIE(InfoExtractor):
head = meta.find(_x('smil:head'))
body = meta.find(_x('smil:body'))
f4m_node = body.find(_x('smil:seq//smil:video'))
f4m_node = body.find(_x('smil:seq//smil:video')) or body.find(_x('smil:seq/smil:video'))
if f4m_node is not None and '.f4m' in f4m_node.attrib['src']:
f4m_url = f4m_node.attrib['src']
if 'manifest.f4m?' not in f4m_url:
@ -127,13 +141,17 @@ class ThePlatformIE(InfoExtractor):
else:
formats = []
switch = body.find(_x('smil:switch'))
if switch is None:
switch = body.find(_x('smil:par//smil:switch')) or body.find(_x('smil:par/smil:switch'))
if switch is None:
switch = body.find(_x('smil:par'))
if switch is not None:
base_url = head.find(_x('smil:meta')).attrib['base']
for f in switch.findall(_x('smil:video')):
attr = f.attrib
width = int(attr['width'])
height = int(attr['height'])
vbr = int(attr['system-bitrate']) // 1000
width = int_or_none(attr.get('width'))
height = int_or_none(attr.get('height'))
vbr = int_or_none(attr.get('system-bitrate'), 1000)
format_id = '%dx%d_%dk' % (width, height, vbr)
formats.append({
'format_id': format_id,
@ -145,10 +163,10 @@ class ThePlatformIE(InfoExtractor):
'vbr': vbr,
})
else:
switch = body.find(_x('smil:seq//smil:switch'))
switch = body.find(_x('smil:seq//smil:switch')) or body.find(_x('smil:seq/smil:switch'))
for f in switch.findall(_x('smil:video')):
attr = f.attrib
vbr = int(attr['system-bitrate']) // 1000
vbr = int_or_none(attr.get('system-bitrate'), 1000)
ext = determine_ext(attr['src'])
if ext == 'once':
ext = 'mp4'
@ -167,5 +185,5 @@ class ThePlatformIE(InfoExtractor):
'formats': formats,
'description': info['description'],
'thumbnail': info['defaultThumbnailUrl'],
'duration': info['duration'] // 1000,
'duration': int_or_none(info.get('duration'), 1000),
}

64
youtube_dl/extractor/udn.py Normal file
View File

@ -0,0 +1,64 @@
# coding: utf-8
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..utils import js_to_json
from ..compat import compat_urlparse
class UDNEmbedIE(InfoExtractor):
_VALID_URL = r'(?:https?:)?//video\.udn\.com/embed/news/(?P<id>\d+)'
_TESTS = [{
'url': 'http://video.udn.com/embed/news/300040',
'md5': 'de06b4c90b042c128395a88f0384817e',
'info_dict': {
'id': '300040',
'ext': 'mp4',
'title': '生物老師男變女 全校挺"做自己"',
'thumbnail': 're:^https?://.*\.jpg$',
}
}, {
'url': '//video.udn.com/embed/news/300040',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
page = self._download_webpage(url, video_id)
options = json.loads(js_to_json(self._html_search_regex(
r'var options\s*=\s*([^;]+);', page, 'video urls dictionary')))
video_urls = options['video']
if video_urls.get('youtube'):
return self.url_result(video_urls.get('youtube'), 'Youtube')
try:
del video_urls['youtube']
except KeyError:
pass
formats = [{
'url': self._download_webpage(
compat_urlparse.urljoin(url, api_url), video_id,
'retrieve url for %s video' % video_type),
'format_id': video_type,
'preference': 0 if video_type == 'mp4' else -1,
} for video_type, api_url in video_urls.items()]
self._sort_formats(formats)
thumbnail = None
if options.get('gallery') and len(options['gallery']):
thumbnail = options['gallery'][0].get('original')
return {
'id': video_id,
'formats': formats,
'title': options['title'],
'thumbnail': thumbnail
}

44
youtube_dl/extractor/vine.py
View File

@ -9,8 +9,8 @@ from ..utils import unified_strdate
class VineIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vine\.co/v/(?P<id>\w+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?vine\.co/(?:v|oembed)/(?P<id>\w+)'
_TESTS = [{
'url': 'https://vine.co/v/b9KOOWX7HUx',
'md5': '2f36fed6235b16da96ce9b4dc890940d',
'info_dict': {
@ -23,21 +23,53 @@ class VineIE(InfoExtractor):
'uploader': 'Jack Dorsey',
'uploader_id': '76',
},
}
}, {
'url': 'https://vine.co/v/MYxVapFvz2z',
'md5': '7b9a7cbc76734424ff942eb52c8f1065',
'info_dict': {
'id': 'MYxVapFvz2z',
'ext': 'mp4',
'title': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
'alt_title': 'Vine by Luna',
'description': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
'upload_date': '20140815',
'uploader': 'Luna',
'uploader_id': '1102363502380728320',
},
}, {
'url': 'https://vine.co/v/bxVjBbZlPUH',
'md5': 'ea27decea3fa670625aac92771a96b73',
'info_dict': {
'id': 'bxVjBbZlPUH',
'ext': 'mp4',
'title': '#mw3 #ac130 #killcam #angelofdeath',
'alt_title': 'Vine by Z3k3',
'description': '#mw3 #ac130 #killcam #angelofdeath',
'upload_date': '20130430',
'uploader': 'Z3k3',
'uploader_id': '936470460173008896',
},
}, {
'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)
data = json.loads(self._html_search_regex(
r'window\.POST_DATA = { %s: ({.+?}) }' % video_id, webpage, 'vine data'))
data = self._parse_json(
self._html_search_regex(
r'window\.POST_DATA = { %s: ({.+?}) };\s*</script>' % video_id,
webpage, 'vine data'),
video_id)
formats = [{
'format_id': '%(format)s-%(rate)s' % f,
'vcodec': f['format'],
'quality': f['rate'],
'url': f['videoUrl'],
} for f in data['videoUrls'] if f.get('rate')]
} for f in data['videoUrls']]
self._sort_formats(formats)

28
youtube_dl/extractor/youtube.py
View File

@ -495,7 +495,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'uploader': '孫艾倫',
'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
},
},
# url_encoded_fmt_stream_map is empty string
{
'url': 'qEJwOuvDf7I',
'info_dict': {
'id': 'qEJwOuvDf7I',
'ext': 'mp4',
'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
'description': '',
'upload_date': '20150404',
'uploader_id': 'spbelect',
'uploader': 'Наблюдатели Петербурга',
},
'params': {
'skip_download': 'requires avconv',
}
},
]
def __init__(self, *args, **kwargs):
@ -772,10 +788,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
errnote='Could not download DASH manifest')
formats = []
for r in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}Representation'):
for a in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}AdaptationSet'):
mime_type = a.attrib.get('mimeType')
for r in a.findall('{urn:mpeg:DASH:schema:MPD:2011}Representation'):
url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL')
if url_el is None:
continue
if mime_type == 'text/vtt':
# TODO implement WebVTT downloading
pass
elif mime_type.startswith('audio/') or mime_type.startswith('video/'):
format_id = r.attrib['id']
video_url = url_el.text
filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength'))
@ -799,6 +821,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
formats.append(full_info)
else:
existing_format.update(f)
else:
self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
return formats
def _real_extract(self, url):
@ -855,7 +879,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
args = ytplayer_config['args']
# Convert to the same format returned by compat_parse_qs
video_info = dict((k, [v]) for k, v in args.items())
if 'url_encoded_fmt_stream_map' not in args:
if not args.get('url_encoded_fmt_stream_map'):
raise ValueError('No stream_map present') # caught below
except ValueError:
# We fallback to the get_video_info pages (used by the embed page)

206
youtube_dl/options.py
View File

@ -13,6 +13,7 @@ from .compat import (
compat_kwargs,
)
from .utils import (
preferredencoding,
write_string,
)
from .version import __version__
@ -120,19 +121,19 @@ def parseOpts(overrideArguments=None):
general.add_option(
'-h', '--help',
action='help',
help='print this help text and exit')
help='Print this help text and exit')
general.add_option(
'-v', '--version',
action='version',
help='print program version and exit')
help='Print program version and exit')
general.add_option(
'-U', '--update',
action='store_true', dest='update_self',
help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
help='Update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
general.add_option(
'-i', '--ignore-errors',
action='store_true', dest='ignoreerrors', default=False,
help='continue on download errors, for example to skip unavailable videos in a playlist')
help='Continue on download errors, for example to skip unavailable videos in a playlist')
general.add_option(
'--abort-on-error',
action='store_false', dest='ignoreerrors',
@ -140,7 +141,7 @@ def parseOpts(overrideArguments=None):
general.add_option(
'--dump-user-agent',
action='store_true', dest='dump_user_agent', default=False,
help='display the current browser identification')
help='Display the current browser identification')
general.add_option(
'--list-extractors',
action='store_true', dest='list_extractors', default=False,
@ -169,7 +170,7 @@ def parseOpts(overrideArguments=None):
'--no-color', '--no-colors',
action='store_true', dest='no_color',
default=False,
help='Do not emit color codes in output.')
help='Do not emit color codes in output')
network = optparse.OptionGroup(parser, 'Network Options')
network.add_option(
@ -206,23 +207,23 @@ def parseOpts(overrideArguments=None):
selection.add_option(
'--playlist-start',
dest='playliststart', metavar='NUMBER', default=1, type=int,
help='playlist video to start at (default is %default)')
help='Playlist video to start at (default is %default)')
selection.add_option(
'--playlist-end',
dest='playlistend', metavar='NUMBER', default=None, type=int,
help='playlist video to end at (default is last)')
help='Playlist video to end at (default is last)')
selection.add_option(
'--playlist-items',
dest='playlist_items', metavar='ITEM_SPEC', default=None,
help='playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8" if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.')
help='Playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8" if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.')
selection.add_option(
'--match-title',
dest='matchtitle', metavar='REGEX',
help='download only matching titles (regex or caseless sub-string)')
help='Download only matching titles (regex or caseless sub-string)')
selection.add_option(
'--reject-title',
dest='rejecttitle', metavar='REGEX',
help='skip download for matching titles (regex or caseless sub-string)')
help='Skip download for matching titles (regex or caseless sub-string)')
selection.add_option(
'--max-downloads',
dest='max_downloads', metavar='NUMBER', type=int, default=None,
@ -238,19 +239,19 @@ def parseOpts(overrideArguments=None):
selection.add_option(
'--date',
metavar='DATE', dest='date', default=None,
help='download only videos uploaded in this date')
help='Download only videos uploaded in this date')
selection.add_option(
'--datebefore',
metavar='DATE', dest='datebefore', default=None,
help='download only videos uploaded on or before this date (i.e. inclusive)')
help='Download only videos uploaded on or before this date (i.e. inclusive)')
selection.add_option(
'--dateafter',
metavar='DATE', dest='dateafter', default=None,
help='download only videos uploaded on or after this date (i.e. inclusive)')
help='Download only videos uploaded on or after this date (i.e. inclusive)')
selection.add_option(
'--min-views',
metavar='COUNT', dest='min_views', default=None, type=int,
help='Do not download any videos with less than COUNT views',)
help='Do not download any videos with less than COUNT views')
selection.add_option(
'--max-views',
metavar='COUNT', dest='max_views', default=None, type=int,
@ -259,7 +260,7 @@ def parseOpts(overrideArguments=None):
'--match-filter',
metavar='FILTER', dest='match_filter', default=None,
help=(
'(Experimental) Generic video filter. '
'Generic video filter (experimental). '
'Specify any key (see help for -o for a list of available keys) to'
' match if the key is present, '
'!key to check if the key is not present,'
@ -277,15 +278,15 @@ def parseOpts(overrideArguments=None):
selection.add_option(
'--no-playlist',
action='store_true', dest='noplaylist', default=False,
help='If the URL refers to a video and a playlist, download only the video.')
help='Download only the video, if the URL refers to a video and a playlist.')
selection.add_option(
'--yes-playlist',
action='store_false', dest='noplaylist', default=False,
help='If the URL refers to a video and a playlist, download the playlist.')
help='Download the playlist, if the URL refers to a video and a playlist.')
selection.add_option(
'--age-limit',
metavar='YEARS', dest='age_limit', default=None, type=int,
help='download only videos suitable for the given age')
help='Download only videos suitable for the given age')
selection.add_option(
'--download-archive', metavar='FILE',
dest='download_archive',
@ -299,30 +300,30 @@ def parseOpts(overrideArguments=None):
authentication.add_option(
'-u', '--username',
dest='username', metavar='USERNAME',
help='login with this account ID')
help='Login with this account ID')
authentication.add_option(
'-p', '--password',
dest='password', metavar='PASSWORD',
help='account password. If this option is left out, youtube-dl will ask interactively.')
help='Account password. If this option is left out, youtube-dl will ask interactively.')
authentication.add_option(
'-2', '--twofactor',
dest='twofactor', metavar='TWOFACTOR',
help='two-factor auth code')
help='Two-factor auth code')
authentication.add_option(
'-n', '--netrc',
action='store_true', dest='usenetrc', default=False,
help='use .netrc authentication data')
help='Use .netrc authentication data')
authentication.add_option(
'--video-password',
dest='videopassword', metavar='PASSWORD',
help='video password (vimeo, smotri)')
help='Video password (vimeo, smotri)')
video_format = optparse.OptionGroup(parser, 'Video Format Options')
video_format.add_option(
'-f', '--format',
action='store', dest='format', metavar='FORMAT', default=None,
help=(
'video format code, specify the order of preference using'
'Video format code, specify the order of preference using'
' slashes, as in -f 22/17/18 . '
' Instead of format codes, you can select by extension for the '
'extensions aac, m4a, mp3, mp4, ogg, wav, webm. '
@ -350,19 +351,19 @@ def parseOpts(overrideArguments=None):
video_format.add_option(
'--all-formats',
action='store_const', dest='format', const='all',
help='download all available video formats')
help='Download all available video formats')
video_format.add_option(
'--prefer-free-formats',
action='store_true', dest='prefer_free_formats', default=False,
help='prefer free video formats unless a specific one is requested')
help='Prefer free video formats unless a specific one is requested')
video_format.add_option(
'--max-quality',
action='store', dest='format_limit', metavar='FORMAT',
help='highest quality format to download')
help='Highest quality format to download')
video_format.add_option(
'-F', '--list-formats',
action='store_true', dest='listformats',
help='list all available formats')
help='List all available formats')
video_format.add_option(
'--youtube-include-dash-manifest',
action='store_true', dest='youtube_include_dash_manifest', default=True,
@ -382,46 +383,46 @@ def parseOpts(overrideArguments=None):
subtitles.add_option(
'--write-sub', '--write-srt',
action='store_true', dest='writesubtitles', default=False,
help='write subtitle file')
help='Write subtitle file')
subtitles.add_option(
'--write-auto-sub', '--write-automatic-sub',
action='store_true', dest='writeautomaticsub', default=False,
help='write automatic subtitle file (youtube only)')
help='Write automatic subtitle file (YouTube only)')
subtitles.add_option(
'--all-subs',
action='store_true', dest='allsubtitles', default=False,
help='downloads all the available subtitles of the video')
help='Download all the available subtitles of the video')
subtitles.add_option(
'--list-subs',
action='store_true', dest='listsubtitles', default=False,
help='lists all available subtitles for the video')
help='List all available subtitles for the video')
subtitles.add_option(
'--sub-format',
action='store', dest='subtitlesformat', metavar='FORMAT', default='best',
help='subtitle format, accepts formats preference, for example: "ass/srt/best"')
help='Subtitle format, accepts formats preference, for example: "srt" or "ass/srt/best"')
subtitles.add_option(
'--sub-lang', '--sub-langs', '--srt-lang',
action='callback', dest='subtitleslangs', metavar='LANGS', type='str',
default=[], callback=_comma_separated_values_options_callback,
help='languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'')
help='Languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'')
downloader = optparse.OptionGroup(parser, 'Download Options')
downloader.add_option(
'-r', '--rate-limit',
dest='ratelimit', metavar='LIMIT',
help='maximum download rate in bytes per second (e.g. 50K or 4.2M)')
help='Maximum download rate in bytes per second (e.g. 50K or 4.2M)')
downloader.add_option(
'-R', '--retries',
dest='retries', metavar='RETRIES', default=10,
help='number of retries (default is %default), or "infinite".')
help='Number of retries (default is %default), or "infinite".')
downloader.add_option(
'--buffer-size',
dest='buffersize', metavar='SIZE', default='1024',
help='size of download buffer (e.g. 1024 or 16K) (default is %default)')
help='Size of download buffer (e.g. 1024 or 16K) (default is %default)')
downloader.add_option(
'--no-resize-buffer',
action='store_true', dest='noresizebuffer', default=False,
help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.')
help='Do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.')
downloader.add_option(
'--test',
action='store_true', dest='test', default=False,
@ -433,11 +434,11 @@ def parseOpts(overrideArguments=None):
downloader.add_option(
'--xattr-set-filesize',
dest='xattr_set_filesize', action='store_true',
help='(experimental) set file xattribute ytdl.filesize with expected filesize')
help='Set file xattribute ytdl.filesize with expected filesize (experimental)')
downloader.add_option(
'--hls-prefer-native',
dest='hls_prefer_native', action='store_true',
help='(experimental) Use the native HLS downloader instead of ffmpeg.')
help='Use the native HLS downloader instead of ffmpeg (experimental)')
downloader.add_option(
'--external-downloader',
dest='external_downloader', metavar='COMMAND',
@ -446,7 +447,7 @@ def parseOpts(overrideArguments=None):
downloader.add_option(
'--external-downloader-args',
dest='external_downloader_args', metavar='ARGS',
help='Give these arguments to the external downloader.')
help='Give these arguments to the external downloader')
workarounds = optparse.OptionGroup(parser, 'Workarounds')
workarounds.add_option(
@ -456,7 +457,7 @@ def parseOpts(overrideArguments=None):
workarounds.add_option(
'--no-check-certificate',
action='store_true', dest='no_check_certificate', default=False,
help='Suppress HTTPS certificate validation.')
help='Suppress HTTPS certificate validation')
workarounds.add_option(
'--prefer-insecure',
'--prefer-unsecure', action='store_true', dest='prefer_insecure',
@ -464,16 +465,16 @@ def parseOpts(overrideArguments=None):
workarounds.add_option(
'--user-agent',
metavar='UA', dest='user_agent',
help='specify a custom user agent')
help='Specify a custom user agent')
workarounds.add_option(
'--referer',
metavar='URL', dest='referer', default=None,
help='specify a custom referer, use if the video access is restricted to one domain',
help='Specify a custom referer, use if the video access is restricted to one domain',
)
workarounds.add_option(
'--add-header',
metavar='FIELD:VALUE', dest='headers', action='append',
help='specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times',
help='Specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times',
)
workarounds.add_option(
'--bidi-workaround',
@ -488,7 +489,7 @@ def parseOpts(overrideArguments=None):
verbosity.add_option(
'-q', '--quiet',
action='store_true', dest='quiet', default=False,
help='activates quiet mode')
help='Activate quiet mode')
verbosity.add_option(
'--no-warnings',
dest='no_warnings', action='store_true', default=False,
@ -496,51 +497,51 @@ def parseOpts(overrideArguments=None):
verbosity.add_option(
'-s', '--simulate',
action='store_true', dest='simulate', default=False,
help='do not download the video and do not write anything to disk',)
help='Do not download the video and do not write anything to disk')
verbosity.add_option(
'--skip-download',
action='store_true', dest='skip_download', default=False,
help='do not download the video',)
help='Do not download the video')
verbosity.add_option(
'-g', '--get-url',
action='store_true', dest='geturl', default=False,
help='simulate, quiet but print URL')
help='Simulate, quiet but print URL')
verbosity.add_option(
'-e', '--get-title',
action='store_true', dest='gettitle', default=False,
help='simulate, quiet but print title')
help='Simulate, quiet but print title')
verbosity.add_option(
'--get-id',
action='store_true', dest='getid', default=False,
help='simulate, quiet but print id')
help='Simulate, quiet but print id')
verbosity.add_option(
'--get-thumbnail',
action='store_true', dest='getthumbnail', default=False,
help='simulate, quiet but print thumbnail URL')
help='Simulate, quiet but print thumbnail URL')
verbosity.add_option(
'--get-description',
action='store_true', dest='getdescription', default=False,
help='simulate, quiet but print video description')
help='Simulate, quiet but print video description')
verbosity.add_option(
'--get-duration',
action='store_true', dest='getduration', default=False,
help='simulate, quiet but print video length')
help='Simulate, quiet but print video length')
verbosity.add_option(
'--get-filename',
action='store_true', dest='getfilename', default=False,
help='simulate, quiet but print output filename')
help='Simulate, quiet but print output filename')
verbosity.add_option(
'--get-format',
action='store_true', dest='getformat', default=False,
help='simulate, quiet but print output format')
help='Simulate, quiet but print output format')
verbosity.add_option(
'-j', '--dump-json',
action='store_true', dest='dumpjson', default=False,
help='simulate, quiet but print JSON information. See --output for a description of available keys.')
help='Simulate, quiet but print JSON information. See --output for a description of available keys.')
verbosity.add_option(
'-J', '--dump-single-json',
action='store_true', dest='dump_single_json', default=False,
help='simulate, quiet but print JSON information for each command-line argument. If the URL refers to a playlist, dump the whole playlist information in a single line.')
help='Simulate, quiet but print JSON information for each command-line argument. If the URL refers to a playlist, dump the whole playlist information in a single line.')
verbosity.add_option(
'--print-json',
action='store_true', dest='print_json', default=False,
@ -549,23 +550,23 @@ def parseOpts(overrideArguments=None):
verbosity.add_option(
'--newline',
action='store_true', dest='progress_with_newline', default=False,
help='output progress bar as new lines')
help='Output progress bar as new lines')
verbosity.add_option(
'--no-progress',
action='store_true', dest='noprogress', default=False,
help='do not print progress bar')
help='Do not print progress bar')
verbosity.add_option(
'--console-title',
action='store_true', dest='consoletitle', default=False,
help='display progress in console titlebar')
help='Display progress in console titlebar')
verbosity.add_option(
'-v', '--verbose',
action='store_true', dest='verbose', default=False,
help='print various debugging information')
help='Print various debugging information')
verbosity.add_option(
'--dump-pages', '--dump-intermediate-pages',
action='store_true', dest='dump_intermediate_pages', default=False,
help='print downloaded pages to debug problems (very verbose)')
help='Print downloaded pages to debug problems (very verbose)')
verbosity.add_option(
'--write-pages',
action='store_true', dest='write_pages', default=False,
@ -581,29 +582,29 @@ def parseOpts(overrideArguments=None):
verbosity.add_option(
'-C', '--call-home',
dest='call_home', action='store_true', default=False,
help='Contact the youtube-dl server for debugging.')
help='Contact the youtube-dl server for debugging')
verbosity.add_option(
'--no-call-home',
dest='call_home', action='store_false', default=False,
help='Do NOT contact the youtube-dl server for debugging.')
help='Do NOT contact the youtube-dl server for debugging')
filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
filesystem.add_option(
'-a', '--batch-file',
dest='batchfile', metavar='FILE',
help='file containing URLs to download (\'-\' for stdin)')
help='File containing URLs to download (\'-\' for stdin)')
filesystem.add_option(
'--id', default=False,
action='store_true', dest='useid', help='use only video ID in file name')
action='store_true', dest='useid', help='Use only video ID in file name')
filesystem.add_option(
'-o', '--output',
dest='outtmpl', metavar='TEMPLATE',
help=('output filename template. Use %(title)s to get the title, '
help=('Output filename template. Use %(title)s to get the title, '
'%(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, '
'%(autonumber)s to get an automatically incremented number, '
'%(ext)s for the filename extension, '
'%(format)s for the format description (like "22 - 1280x720" or "HD"), '
'%(format_id)s for the unique id of the format (like Youtube\'s itags: "137"), '
'%(format_id)s for the unique id of the format (like YouTube\'s itags: "137"), '
'%(upload_date)s for the upload date (YYYYMMDD), '
'%(extractor)s for the provider (youtube, metacafe, etc), '
'%(id)s for the video id, '
@ -617,7 +618,7 @@ def parseOpts(overrideArguments=None):
filesystem.add_option(
'--autonumber-size',
dest='autonumber_size', metavar='NUMBER',
help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given')
help='Specify the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given')
filesystem.add_option(
'--restrict-filenames',
action='store_true', dest='restrictfilenames', default=False,
@ -625,55 +626,55 @@ def parseOpts(overrideArguments=None):
filesystem.add_option(
'-A', '--auto-number',
action='store_true', dest='autonumber', default=False,
help='[deprecated; use -o "%(autonumber)s-%(title)s.%(ext)s" ] number downloaded files starting from 00000')
help='[deprecated; use -o "%(autonumber)s-%(title)s.%(ext)s" ] Number downloaded files starting from 00000')
filesystem.add_option(
'-t', '--title',
action='store_true', dest='usetitle', default=False,
help='[deprecated] use title in file name (default)')
help='[deprecated] Use title in file name (default)')
filesystem.add_option(
'-l', '--literal', default=False,
action='store_true', dest='usetitle',
help='[deprecated] alias of --title')
help='[deprecated] Alias of --title')
filesystem.add_option(
'-w', '--no-overwrites',
action='store_true', dest='nooverwrites', default=False,
help='do not overwrite files')
help='Do not overwrite files')
filesystem.add_option(
'-c', '--continue',
action='store_true', dest='continue_dl', default=True,
help='force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.')
help='Force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.')
filesystem.add_option(
'--no-continue',
action='store_false', dest='continue_dl',
help='do not resume partially downloaded files (restart from beginning)')
help='Do not resume partially downloaded files (restart from beginning)')
filesystem.add_option(
'--no-part',
action='store_true', dest='nopart', default=False,
help='do not use .part files - write directly into output file')
help='Do not use .part files - write directly into output file')
filesystem.add_option(
'--no-mtime',
action='store_false', dest='updatetime', default=True,
help='do not use the Last-modified header to set the file modification time')
help='Do not use the Last-modified header to set the file modification time')
filesystem.add_option(
'--write-description',
action='store_true', dest='writedescription', default=False,
help='write video description to a .description file')
help='Write video description to a .description file')
filesystem.add_option(
'--write-info-json',
action='store_true', dest='writeinfojson', default=False,
help='write video metadata to a .info.json file')
help='Write video metadata to a .info.json file')
filesystem.add_option(
'--write-annotations',
action='store_true', dest='writeannotations', default=False,
help='write video annotations to a .annotation file')
help='Write video annotations to a .annotation file')
filesystem.add_option(
'--load-info',
dest='load_info_filename', metavar='FILE',
help='json file containing the video information (created with the "--write-json" option)')
help='JSON file containing the video information (created with the "--write-info-json" option)')
filesystem.add_option(
'--cookies',
dest='cookiefile', metavar='FILE',
help='file to read cookies from and dump cookie jar in')
help='File to read cookies from and dump cookie jar in')
filesystem.add_option(
'--cache-dir', dest='cachedir', default=None, metavar='DIR',
help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.')
@ -689,11 +690,11 @@ def parseOpts(overrideArguments=None):
thumbnail.add_option(
'--write-thumbnail',
action='store_true', dest='writethumbnail', default=False,
help='write thumbnail image to disk')
help='Write thumbnail image to disk')
thumbnail.add_option(
'--write-all-thumbnails',
action='store_true', dest='write_all_thumbnails', default=False,
help='write all thumbnail image formats to disk')
help='Write all thumbnail image formats to disk')
thumbnail.add_option(
'--list-thumbnails',
action='store_true', dest='list_thumbnails', default=False,
@ -703,14 +704,14 @@ def parseOpts(overrideArguments=None):
postproc.add_option(
'-x', '--extract-audio',
action='store_true', dest='extractaudio', default=False,
help='convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
help='Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
postproc.add_option(
'--audio-format', metavar='FORMAT', dest='audioformat', default='best',
help='"best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "%default" by default')
help='Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "%default" by default')
postproc.add_option(
'--audio-quality', metavar='QUALITY',
dest='audioquality', default='5',
help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default %default)')
help='Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default %default)')
postproc.add_option(
'--recode-video',
metavar='FORMAT', dest='recodevideo', default=None,
@ -718,27 +719,27 @@ def parseOpts(overrideArguments=None):
postproc.add_option(
'-k', '--keep-video',
action='store_true', dest='keepvideo', default=False,
help='keeps the video file on disk after the post-processing; the video is erased by default')
help='Keep the video file on disk after the post-processing; the video is erased by default')
postproc.add_option(
'--no-post-overwrites',
action='store_true', dest='nopostoverwrites', default=False,
help='do not overwrite post-processed files; the post-processed files are overwritten by default')
help='Do not overwrite post-processed files; the post-processed files are overwritten by default')
postproc.add_option(
'--embed-subs',
action='store_true', dest='embedsubtitles', default=False,
help='embed subtitles in the video (only for mp4 videos)')
help='Embed subtitles in the video (only for mp4 videos)')
postproc.add_option(
'--embed-thumbnail',
action='store_true', dest='embedthumbnail', default=False,
help='embed thumbnail in the audio as cover art')
help='Embed thumbnail in the audio as cover art')
postproc.add_option(
'--add-metadata',
action='store_true', dest='addmetadata', default=False,
help='write metadata to the video file')
help='Write metadata to the video file')
postproc.add_option(
'--metadata-from-title',
metavar='FORMAT', dest='metafromtitle',
help='parse additional metadata like song title / artist from the video title. '
help='Parse additional metadata like song title / artist from the video title. '
'The format syntax is the same as --output, '
'the parsed parameters replace existing values. '
'Additional templates: %(album), %(artist). '
@ -747,7 +748,7 @@ def parseOpts(overrideArguments=None):
postproc.add_option(
'--xattrs',
action='store_true', dest='xattrs', default=False,
help='write metadata to the video file\'s xattrs (using dublin core and xdg standards)')
help='Write metadata to the video file\'s xattrs (using dublin core and xdg standards)')
postproc.add_option(
'--fixup',
metavar='POLICY', dest='fixup', default='detect_or_warn',
@ -793,21 +794,22 @@ def parseOpts(overrideArguments=None):
if opts.verbose:
write_string('[debug] Override config: ' + repr(overrideArguments) + '\n')
else:
command_line_conf = sys.argv[1:]
# Workaround for Python 2.x, where argv is a byte list
def compat_conf(conf):
if sys.version_info < (3,):
command_line_conf = [
a.decode('utf-8', 'replace') for a in command_line_conf]
return [a.decode(preferredencoding(), 'replace') for a in conf]
return conf
command_line_conf = compat_conf(sys.argv[1:])
if '--ignore-config' in command_line_conf:
system_conf = []
user_conf = []
else:
system_conf = _readOptions('/etc/youtube-dl.conf')
system_conf = compat_conf(_readOptions('/etc/youtube-dl.conf'))
if '--ignore-config' in system_conf:
user_conf = []
else:
user_conf = _readUserConf()
user_conf = compat_conf(_readUserConf())
argv = system_conf + user_conf + command_line_conf
opts, args = parser.parse_args(argv)

13
youtube_dl/postprocessor/common.py
View File

@ -1,6 +1,11 @@
from __future__ import unicode_literals
from ..utils import PostProcessingError
import os
from ..utils import (
PostProcessingError,
encodeFilename,
)
class PostProcessor(object):
@ -46,6 +51,12 @@ class PostProcessor(object):
"""
return None, information # by default, keep file and do nothing
def try_utime(self, path, atime, mtime, errnote='Cannot update utime of file'):
try:
os.utime(encodeFilename(path), (atime, mtime))
except Exception:
self._downloader.report_warning(errnote)
class AudioConversionError(PostProcessingError):
pass

16
youtube_dl/postprocessor/ffmpeg.py
View File

@ -116,6 +116,10 @@ class FFmpegPostProcessor(PostProcessor):
def executable(self):
return self._paths[self.basename]
@property
def probe_available(self):
return self.probe_basename is not None
@property
def probe_executable(self):
return self._paths[self.probe_basename]
@ -142,7 +146,8 @@ class FFmpegPostProcessor(PostProcessor):
stderr = stderr.decode('utf-8', 'replace')
msg = stderr.strip().split('\n')[-1]
raise FFmpegPostProcessorError(msg)
os.utime(encodeFilename(out_path), (oldest_mtime, oldest_mtime))
self.try_utime(out_path, oldest_mtime, oldest_mtime)
if self._deletetempfiles:
for ipath in input_paths:
os.remove(ipath)
@ -168,7 +173,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
def get_audio_codec(self, path):
if not self.probe_executable:
if not self.probe_available:
raise PostProcessingError('ffprobe or avprobe not found. Please install one.')
try:
cmd = [
@ -276,10 +281,9 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
# Try to update the date time for extracted audio file.
if information.get('filetime') is not None:
try:
os.utime(encodeFilename(new_path), (time.time(), information['filetime']))
except Exception:
self._downloader.report_warning('Cannot update utime of audio file')
self.try_utime(
new_path, time.time(), information['filetime'],
errnote='Cannot update utime of audio file')
information['filepath'] = new_path
return self._nopostoverwrites, information

5
youtube_dl/utils.py
View File

@ -730,6 +730,7 @@ def unified_strdate(date_str, day_first=True):
# Replace commas
date_str = date_str.replace(',', ' ')
# %z (UTC offset) is only supported in python>=3.2
if not re.match(r'^[0-9]{1,2}-[0-9]{1,2}-[0-9]{4}$', date_str):
date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str)
# Remove AM/PM + timezone
date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
@ -759,6 +760,7 @@ def unified_strdate(date_str, day_first=True):
]
if day_first:
format_expressions.extend([
'%d-%m-%Y',
'%d.%m.%Y',
'%d/%m/%Y',
'%d/%m/%y',
@ -766,6 +768,7 @@ def unified_strdate(date_str, day_first=True):
])
else:
format_expressions.extend([
'%m-%d-%Y',
'%m.%d.%Y',
'%m/%d/%Y',
'%m/%d/%y',
@ -1577,7 +1580,7 @@ def js_to_json(code):
'(?:[^'\\]*(?:\\\\|\\['"nu]))*[^'\\]*'|
[a-zA-Z_][.a-zA-Z_0-9]*
''', fix_kv, code)
res = re.sub(r',(\s*\])', lambda m: m.group(1), res)
res = re.sub(r',(\s*[\]}])', lambda m: m.group(1), res)
return res

2
youtube_dl/version.py
View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2015.04.03'
__version__ = '2015.04.09'