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

First commit to show implementation

Browse Source
This commit is contained in:
Filippo Valsorda 2013-06-05 11:30:34 +02:00
parent 1b2b22ed9f
commit d47e2518f0
12 changed files with 1142 additions and 4936 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
Makefile
View File

@ -40,15 +40,15 @@ tar: youtube-dl.tar.gz
pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1
youtube-dl: youtube_dl/*.py
zip --quiet youtube-dl youtube_dl/*.py
youtube-dl: youtube_dl/*.py youtube_dl/InfoExtractors/*.py
zip --quiet youtube-dl youtube_dl/*.py youtube_dl/InfoExtractors/*.py
zip --quiet --junk-paths youtube-dl youtube_dl/__main__.py
echo '#!$(PYTHON)' > youtube-dl
cat youtube-dl.zip >> youtube-dl
rm youtube-dl.zip
chmod a+x youtube-dl
README.md: youtube_dl/*.py
README.md: youtube_dl/*.py youtube_dl/InfoExtractors/*.py
COLUMNS=80 python -m youtube_dl --help | python devscripts/make_readme.py
README.txt: README.md
@ -57,7 +57,7 @@ README.txt: README.md
youtube-dl.1: README.md
pandoc -s -f markdown -t man README.md -o youtube-dl.1
youtube-dl.bash-completion: youtube_dl/*.py devscripts/bash-completion.in
youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/InfoExtractors/*.py devscripts/bash-completion.in
python devscripts/bash-completion.py
bash-completion: youtube-dl.bash-completion

7
setup.py
View File

@ -4,6 +4,7 @@
from __future__ import print_function
import pkg_resources
import sys
from glob import glob
try:
from setuptools import setup
@ -23,7 +24,9 @@ py2exe_options = {
"compressed": 1,
"optimize": 2,
"dist_dir": '.',
"dll_excludes": ['w9xpopen.exe']
"dll_excludes": ['w9xpopen.exe'],
"includes": [ m.replace('\\', '.').replace('/', '.')[:-3]
for m in glob('youtube_dl/InfoExtractors/*.py') ]
}
py2exe_console = [{
"script": "./youtube_dl/__main__.py",
@ -57,7 +60,7 @@ setup(
author = 'Ricardo Garcia',
maintainer = 'Philipp Hagemeister',
maintainer_email = 'phihag@phihag.de',
packages = ['youtube_dl'],
packages = ['youtube_dl', 'youtube_dl.InfoExtractors'],
# Provokes warning on most systems (why?!)
#test_suite = 'nose.collector',

6
test/test_all_urls.py
View File

@ -7,7 +7,11 @@ import unittest
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE, YoutubeChannelIE
from youtube_dl.InfoExtractors import get_info_extractor
YoutubeIE = get_info_extractor('Youtube')
YoutubePlaylistIE = get_info_extractor('YoutubePlaylist')
YoutubeChannelIE = get_info_extractor('YoutubeChannel')
class TestAllURLsMatching(unittest.TestCase):
def test_youtube_playlist_matching(self):

2
test/test_write_info_json.py
View File

@ -48,7 +48,7 @@ class TestInfoJSON(unittest.TestCase):
self.tearDown()
def test_info_json(self):
ie = youtube_dl.InfoExtractors.YoutubeIE()
ie = youtube_dl.InfoExtractors.get_info_extractor('Youtube')()
fd = FileDownloader(params)
fd.add_info_extractor(ie)
fd.download([TEST_ID])

7
test/test_youtube_lists.py
View File

@ -8,9 +8,14 @@ import json
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.InfoExtractors import YoutubeUserIE, YoutubePlaylistIE, YoutubeIE, YoutubeChannelIE
from youtube_dl.utils import *
from youtube_dl.FileDownloader import FileDownloader
from youtube_dl.InfoExtractors import get_info_extractor
YoutubeIE = get_info_extractor('Youtube')
YoutubePlaylistIE = get_info_extractor('YoutubePlaylist')
YoutubeChannelIE = get_info_extractor('YoutubeChannel')
YoutubeUserIE = get_info_extractor('YoutubeUser')
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:

4
test/test_youtube_subtitles.py
View File

@ -10,9 +10,11 @@ import hashlib
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.InfoExtractors import YoutubeIE
from youtube_dl.utils import *
from youtube_dl import FileDownloader
from youtube_dl.InfoExtractors import get_info_extractor
YoutubeIE = get_info_extractor('Youtube')
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:

466
test/tests.json
View File

@ -11,476 +11,10 @@
"description": "test chars: \"'/\\ä↭𝕐\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de ."
}
},
{
"name": "Dailymotion",
"md5": "392c4b85a60a90dc4792da41ce3144eb",
"url": "http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech",
"file": "x33vw9.mp4"
},
{
"name": "Metacafe",
"add_ie": ["Youtube"],
"url": "http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
"file": "_aUehQsCQtM.flv"
},
{
"name": "BlipTV",
"md5": "b2d849efcf7ee18917e4b4d9ff37cafe",
"url": "http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352",
"file": "5779306.m4v"
},
{
"name": "XVideos",
"md5": "1d0c835822f0a71a7bf011855db929d0",
"url": "http://www.xvideos.com/video939581/funny_porns_by_s_-1",
"file": "939581.flv"
},
{
"name": "YouPorn",
"md5": "c37ddbaaa39058c76a7e86c6813423c1",
"url": "http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/",
"file": "505835.mp4"
},
{
"name": "Pornotube",
"md5": "374dd6dcedd24234453b295209aa69b6",
"url": "http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing",
"file": "1689755.flv"
},
{
"name": "YouJizz",
"md5": "07e15fa469ba384c7693fd246905547c",
"url": "http://www.youjizz.com/videos/zeichentrick-1-2189178.html",
"file": "2189178.flv"
},
{
"name": "Vimeo",
"md5": "8879b6cc097e987f02484baf890129e5",
"url": "http://vimeo.com/56015672",
"file": "56015672.mp4",
"info_dict": {
"title": "youtube-dl test video - ★ \" ' 幸 / \\ ä ↭ 𝕐",
"uploader": "Filippo Valsorda",
"uploader_id": "user7108434",
"upload_date": "20121220",
"description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: ★ \" ' 幸 / \\ ä ↭ 𝕐"
}
},
{
"name": "Soundcloud",
"md5": "ebef0a451b909710ed1d7787dddbf0d7",
"url": "http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy",
"file": "62986583.mp3"
},
{
"name": "StanfordOpenClassroom",
"md5": "544a9468546059d4e80d76265b0443b8",
"url": "http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100",
"file": "PracticalUnix_intro-environment.mp4"
},
{
"name": "XNXX",
"md5": "0831677e2b4761795f68d417e0b7b445",
"url": "http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_",
"file": "1135332.flv"
},
{
"name": "Youku",
"url": "http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html",
"file": "XNDgyMDQ2NTQw_part00.flv",
"md5": "ffe3f2e435663dc2d1eea34faeff5b5b",
"params": { "test": false }
},
{
"name": "NBA",
"url": "http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html",
"file": "0021200253-okc-bkn-recap.nba.mp4",
"md5": "c0edcfc37607344e2ff8f13c378c88a4"
},
{
"name": "JustinTV",
"url": "http://www.twitch.tv/thegamedevhub/b/296128360",
"file": "296128360.flv",
"md5": "ecaa8a790c22a40770901460af191c9a"
},
{
"name": "MyVideo",
"url": "http://www.myvideo.de/watch/8229274/bowling_fail_or_win",
"file": "8229274.flv",
"md5": "2d2753e8130479ba2cb7e0a37002053e"
},
{
"name": "Escapist",
"url": "http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate",
"file": "6618-Breaking-Down-Baldurs-Gate.mp4",
"md5": "c6793dbda81388f4264c1ba18684a74d"
},
{
"name": "GooglePlus",
"url": "https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH",
"file": "ZButuJc6CtH.flv"
},
{
"name": "FunnyOrDie",
"url": "http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version",
"file": "0732f586d7.mp4",
"md5": "f647e9e90064b53b6e046e75d0241fbd"
},
{
"name": "Steam",
"url": "http://store.steampowered.com/video/105600/",
"playlist": [
{
"file": "81300.flv",
"md5": "f870007cee7065d7c76b88f0a45ecc07",
"info_dict": {
"title": "Terraria 1.1 Trailer"
}
},
{
"file": "80859.flv",
"md5": "61aaf31a5c5c3041afb58fb83cbb5751",
"info_dict": {
"title": "Terraria Trailer"
}
}
]
},
{
"name": "Ustream",
"url": "http://www.ustream.tv/recorded/20274954",
"file": "20274954.flv",
"md5": "088f151799e8f572f84eb62f17d73e5c",
"info_dict": {
"title": "Young Americans for Liberty February 7, 2012 2:28 AM",
"uploader": "Young Americans for Liberty"
}
},
{
"name": "InfoQ",
"url": "http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
"file": "12-jan-pythonthings.mp4",
"info_dict": {
"title": "A Few of My Favorite [Python] Things"
},
"params": {
"skip_download": true
}
},
{
"name": "ComedyCentral",
"url": "http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart",
"file": "422212.mp4",
"md5": "4e2f5cb088a83cd8cdb7756132f9739d",
"info_dict": {
"title": "thedailyshow-kristen-stewart part 1"
}
},
{
"name": "RBMARadio",
"url": "http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011",
"file": "ford-lopatin-live-at-primavera-sound-2011.mp3",
"md5": "6bc6f9bcb18994b4c983bc3bf4384d95",
"info_dict": {
"title": "Live at Primavera Sound 2011",
"description": "Joel Ford and Daniel \u2019Oneohtrix Point Never\u2019 Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.",
"uploader": "Ford & Lopatin",
"uploader_id": "ford-lopatin",
"location": "Spain"
}
},
{
"name": "Facebook",
"url": "https://www.facebook.com/photo.php?v=120708114770723",
"file": "120708114770723.mp4",
"md5": "48975a41ccc4b7a581abd68651c1a5a8",
"info_dict": {
"title": "PEOPLE ARE AWESOME 2013",
"duration": 279
}
},
{
"name": "EightTracks",
"url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
"playlist": [
{
"file": "11885610.m4a",
"md5": "96ce57f24389fc8734ce47f4c1abcc55",
"info_dict": {
"title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
}
},
{
"file": "11885608.m4a",
"md5": "4ab26f05c1f7291ea460a3920be8021f",
"info_dict": {
"title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
}
},
{
"file": "11885679.m4a",
"md5": "d30b5b5f74217410f4689605c35d1fd7",
"info_dict": {
"title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad"
}
},
{
"file": "11885680.m4a",
"md5": "4eb0a669317cd725f6bbd336a29f923a",
"info_dict": {
"title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad"
}
},
{
"file": "11885682.m4a",
"md5": "1893e872e263a2705558d1d319ad19e8",
"info_dict": {
"title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad"
}
},
{
"file": "11885683.m4a",
"md5": "b673c46f47a216ab1741ae8836af5899",
"info_dict": {
"title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad"
}
},
{
"file": "11885684.m4a",
"md5": "1d74534e95df54986da7f5abf7d842b7",
"info_dict": {
"title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad"
}
},
{
"file": "11885685.m4a",
"md5": "f081f47af8f6ae782ed131d38b9cd1c0",
"info_dict": {
"title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad"
}
}
]
},
{
"name": "Keek",
"url": "http://www.keek.com/ytdl/keeks/NODfbab",
"file": "NODfbab.mp4",
"md5": "9b0636f8c0f7614afa4ea5e4c6e57e83",
"info_dict": {
"title": "test chars: \"'/\\ä<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de ."
}
},
{
"name": "TED",
"url": "http://www.ted.com/talks/dan_dennett_on_our_consciousness.html",
"file": "102.mp4",
"md5": "7bc087e71d16f18f9b8ab9fa62a8a031",
"info_dict": {
"title": "Dan Dennett: The illusion of consciousness",
"thumbnail": "http://images.ted.com/images/ted/488_389x292.jpg"
}
},
{
"name": "MySpass",
"url": "http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/",
"file": "11741.mp4",
"md5": "0b49f4844a068f8b33f4b7c88405862b",
"info_dict": {
"title": "Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2"
}
},
{
"name": "Generic",
"url": "http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html",
"file": "13601338388002.mp4",
"md5": "85b90ccc9d73b4acd9138d3af4c27f89"
},
{
"name": "Spiegel",
"url": "http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html",
"file": "1259285.mp4",
"md5": "2c2754212136f35fb4b19767d242f66e",
"info_dict": {
"title": "Vulkanausbruch in Ecuador: Der \"Feuerschlund\" ist wieder aktiv"
}
},
{
"name": "LiveLeak",
"md5": "0813c2430bea7a46bf13acf3406992f4",
"url": "http://www.liveleak.com/view?i=757_1364311680",
"file": "757_1364311680.mp4",
"info_dict": {
"title": "Most unlucky car accident",
"description": "extremely bad day for this guy..!",
"uploader": "ljfriel2"
}
},
{
"name": "WorldStarHipHop",
"url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO",
"file": "wshh6a7q1ny0G34ZwuIO.mp4",
"md5": "9d04de741161603bf7071bbf4e883186",
"info_dict": {
"title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick! "
}
},
{
"name": "ARD",
"url": "http://www.ardmediathek.de/das-erste/tagesschau-in-100-sek?documentId=14077640",
"file": "14077640.mp4",
"md5": "6ca8824255460c787376353f9e20bbd8",
"info_dict": {
"title": "11.04.2013 09:23 Uhr - Tagesschau in 100 Sekunden"
},
"skip": "Requires rtmpdump"
},
{
"name": "Tumblr",
"url": "http://birthdayproject2012.tumblr.com/post/17258355236/a-sample-video-from-leeann-if-you-need-an-idea",
"file": "17258355236.mp4",
"md5": "7c6a514d691b034ccf8567999e9e88a3",
"info_dict": {
"title": "Calling all Pris! - A sample video from LeeAnn. (If you need an idea..."
}
},
{
"name": "SoundcloudSet",
"url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
"playlist":[
{
"file":"30510138.mp3",
"md5":"f9136bf103901728f29e419d2c70f55d",
"info_dict": {
"title":"D-D-Dance"
}
},
{
"file":"47127625.mp3",
"md5":"09b6758a018470570f8fd423c9453dd8",
"info_dict": {
"title":"The Royal Concept - Gimme Twice"
}
},
{
"file":"47127627.mp3",
"md5":"154abd4e418cea19c3b901f1e1306d9c",
"info_dict": {
"title":"Goldrushed"
}
},
{
"file":"47127629.mp3",
"md5":"2f5471edc79ad3f33a683153e96a79c1",
"info_dict": {
"title":"In the End"
}
},
{
"file":"47127631.mp3",
"md5":"f9ba87aa940af7213f98949254f1c6e2",
"info_dict": {
"title":"Knocked Up"
}
},
{
"file":"75206121.mp3",
"md5":"f9d1fe9406717e302980c30de4af9353",
"info_dict": {
"title":"World On Fire"
}
}
]
},
{
"name":"Bandcamp",
"url":"http://youtube-dl.bandcamp.com/track/youtube-dl-test-song",
"file":"1812978515.mp3",
"md5":"cdeb30cdae1921719a3cbcab696ef53c",
"info_dict": {
"title":"youtube-dl test song \"'/\\ä↭"
},
"skip": "There is a limit of 200 free downloads / month for the test song"
},
{
"name": "RedTube",
"url": "http://www.redtube.com/66418",
"file": "66418.mp4",
"md5": "7b8c22b5e7098a3e1c09709df1126d2d",
"info_dict":{
"title":"Sucked on a toilet"
}
},
{
"name": "Photobucket",
"url": "http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0",
"file": "zpsc0c3b9fa.mp4",
"md5": "7dabfb92b0a31f6c16cebc0f8e60ff99",
"info_dict":{
"title":"Tired of Link Building? Try BacklinkMyDomain.com!"
}
},
{
"name": "Ina",
"url": "www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html",
"file": "I12055569.mp4",
"md5": "a667021bf2b41f8dc6049479d9bb38a3",
"info_dict":{
"title":"François Hollande \"Je crois que c'est clair\""
}
},
{
"name": "Yahoo",
"url": "http://screen.yahoo.com/obama-celebrates-iraq-victory-27592561.html",
"file": "27592561.flv",
"md5": "c6179bed843512823fd284fa2e7f012d",
"info_dict": {
"title": "Obama Celebrates Iraq Victory"
},
"skip": "Requires rtmpdump"
},
{
"name": "Howcast",
"url": "http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly",
"file": "390161.mp4",
"md5": "1d7ba54e2c9d7dc6935ef39e00529138",
"info_dict":{
"title":"How to Tie a Square Knot Properly",
"description":"The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here's the proper way to tie a square knot."
}
},
{
"name": "Vine",
"url": "https://vine.co/v/b9KOOWX7HUx",
"file": "b9KOOWX7HUx.mp4",
"md5": "2f36fed6235b16da96ce9b4dc890940d",
"info_dict":{
"title": "Chicken.",
"uploader": "Jack Dorsey"
}
},
{
"name": "Flickr",
"url": "http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/",
"file": "5645318632.mp4",
"md5": "6fdc01adbc89d72fc9c4f15b4a4ba87b",
"info_dict":{
"title": "Dark Hollow Waterfalls",
"uploader_id": "forestwander-nature-pictures",
"description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up."
}
},
{
"name": "Teamcoco",
"url": "http://teamcoco.com/video/louis-ck-interview-george-w-bush",
"file": "19705.mp4",
"md5": "27b6f7527da5acf534b15f21b032656e",
"info_dict":{
"title": "Louis C.K. Interview Pt. 1 11/3/11",
"description": "Louis C.K. got starstruck by George W. Bush, so what? Part one."
}
}
]

4460
youtube_dl/InfoExtractors.py
View File

File diff suppressed because it is too large Load Diff

145
youtube_dl/InfoExtractors/Generic.py Normal file
View File

@ -0,0 +1,145 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import absolute_import
import os
import re
from ..utils import *
from .InfoExtractor import InfoExtractor
class GenericIE(InfoExtractor):
"""Generic last-resort information extractor."""
_VALID_URL = r'.*'
IE_NAME = u'generic'
def report_download_webpage(self, video_id):
"""Report webpage download."""
if not self._downloader.params.get('test', False):
self._downloader.report_warning(u'Falling back on generic information extractor.')
super(GenericIE, self).report_download_webpage(video_id)
def report_following_redirect(self, new_url):
"""Report information extraction."""
self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url)
def _test_redirect(self, url):
"""Check if it is a redirect, like url shorteners, in case return the new url."""
class HeadRequest(compat_urllib_request.Request):
def get_method(self):
return "HEAD"
class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
"""
Subclass the HTTPRedirectHandler to make it use our
HeadRequest also on the redirected URL
"""
def redirect_request(self, req, fp, code, msg, headers, newurl):
if code in (301, 302, 303, 307):
newurl = newurl.replace(' ', '%20')
newheaders = dict((k,v) for k,v in req.headers.items()
if k.lower() not in ("content-length", "content-type"))
return HeadRequest(newurl,
headers=newheaders,
origin_req_host=req.get_origin_req_host(),
unverifiable=True)
else:
raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
class HTTPMethodFallback(compat_urllib_request.BaseHandler):
"""
Fallback to GET if HEAD is not allowed (405 HTTP error)
"""
def http_error_405(self, req, fp, code, msg, headers):
fp.read()
fp.close()
newheaders = dict((k,v) for k,v in req.headers.items()
if k.lower() not in ("content-length", "content-type"))
return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
headers=newheaders,
origin_req_host=req.get_origin_req_host(),
unverifiable=True))
# Build our opener
opener = compat_urllib_request.OpenerDirector()
for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
HTTPMethodFallback, HEADRedirectHandler,
compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
opener.add_handler(handler())
response = opener.open(HeadRequest(url))
if response is None:
raise ExtractorError(u'Invalid URL protocol')
new_url = response.geturl()
if url == new_url:
return False
self.report_following_redirect(new_url)
return new_url
def _real_extract(self, url):
new_url = self._test_redirect(url)
if new_url: return [self.url_result(new_url)]
video_id = url.split('/')[-1]
try:
webpage = self._download_webpage(url, video_id)
except ValueError as err:
# since this is the last-resort InfoExtractor, if
# this error is thrown, it'll be thrown here
raise ExtractorError(u'Invalid URL: %s' % url)
self.report_extraction(video_id)
# Start with something easy: JW Player in SWFObject
mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
if mobj is None:
# Broaden the search a little bit
mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
if mobj is None:
# Broaden the search a little bit: JWPlayer JS loader
mobj = re.search(r'[^A-Za-z0-9]?file:\s*["\'](http[^\'"&]*)', webpage)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
# It's possible that one of the regexes
# matched, but returned an empty group:
if mobj.group(1) is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_url = compat_urllib_parse.unquote(mobj.group(1))
video_id = os.path.basename(video_url)
# here's a fun little line of code for you:
video_extension = os.path.splitext(video_id)[1][1:]
video_id = os.path.splitext(video_id)[0]
# it's tempting to parse this further, but you would
# have to take into account all the variations like
# Video Title - Site Name
# Site Name | Video Title
# Video Title - Tagline | Site Name
# and so on and so forth; it's just not practical
mobj = re.search(r'<title>(.*)</title>', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract title')
video_title = mobj.group(1)
# video uploader is domain name
mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
if mobj is None:
raise ExtractorError(u'Unable to extract title')
video_uploader = mobj.group(1)
return [{
'id': video_id,
'url': video_url,
'uploader': video_uploader,
'upload_date': None,
'title': video_title,
'ext': video_extension,
}]

218
youtube_dl/InfoExtractors/InfoExtractor.py Normal file
View File

@ -0,0 +1,218 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import absolute_import
import base64
import re
import socket
from ..utils import *
class InfoExtractor(object):
"""Information Extractor class.
Information extractors are the classes that, given a URL, extract
information about the video (or videos) the URL refers to. This
information includes the real video URL, the video title, author and
others. The information is stored in a dictionary which is then
passed to the FileDownloader. The FileDownloader processes this
information possibly downloading the video to the file system, among
other possible outcomes.
The dictionaries must include the following fields:
id: Video identifier.
url: Final video URL.
title: Video title, unescaped.
ext: Video filename extension.
The following fields are optional:
format: The video format, defaults to ext (used for --get-format)
thumbnail: Full URL to a video thumbnail image.
description: One-line video description.
uploader: Full name of the video uploader.
upload_date: Video upload date (YYYYMMDD).
uploader_id: Nickname or id of the video uploader.
location: Physical location of the video.
player_url: SWF Player URL (used for rtmpdump).
subtitles: The subtitle file contents.
urlhandle: [internal] The urlHandle to be used to download the file,
like returned by urllib.request.urlopen
The fields should all be Unicode strings.
Subclasses of this one should re-define the _real_initialize() and
_real_extract() methods and define a _VALID_URL regexp.
Probably, they should also be added to the list of extractors.
_real_extract() must return a *list* of information dictionaries as
described above.
Finally, the _WORKING attribute should be set to False for broken IEs
in order to warn the users and skip the tests.
"""
_ready = False
_downloader = None
_WORKING = True
def __init__(self, downloader=None):
"""Constructor. Receives an optional downloader."""
self._ready = False
self.set_downloader(downloader)
@classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(cls._VALID_URL, url) is not None
@classmethod
def working(cls):
"""Getter method for _WORKING."""
return cls._WORKING
def initialize(self):
"""Initializes an instance (authentication, etc)."""
if not self._ready:
self._real_initialize()
self._ready = True
def extract(self, url):
"""Extracts URL information and returns it in list of dicts."""
self.initialize()
return self._real_extract(url)
def set_downloader(self, downloader):
"""Sets the downloader for this IE."""
self._downloader = downloader
def _real_initialize(self):
"""Real initialization process. Redefine in subclasses."""
pass
def _real_extract(self, url):
"""Real extraction process. Redefine in subclasses."""
pass
@property
def IE_NAME(self):
return type(self).__name__[:-2]
def _request_webpage(self, url_or_request, video_id, note=None, errnote=None):
""" Returns the response handle """
if note is None:
self.report_download_webpage(video_id)
elif note is not False:
self.to_screen(u'%s: %s' % (video_id, note))
try:
return compat_urllib_request.urlopen(url_or_request)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
if errnote is None:
errnote = u'Unable to download webpage'
raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
""" Returns a tuple (page content as string, URL handle) """
urlh = self._request_webpage(url_or_request, video_id, note, errnote)
content_type = urlh.headers.get('Content-Type', '')
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
if m:
encoding = m.group(1)
else:
encoding = 'utf-8'
webpage_bytes = urlh.read()
if self._downloader.params.get('dump_intermediate_pages', False):
try:
url = url_or_request.get_full_url()
except AttributeError:
url = url_or_request
self.to_screen(u'Dumping request to ' + url)
dump = base64.b64encode(webpage_bytes).decode('ascii')
self._downloader.to_screen(dump)
content = webpage_bytes.decode(encoding, 'replace')
return (content, urlh)
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
""" Returns the data of the page as a string """
return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0]
def to_screen(self, msg):
"""Print msg to screen, prefixing it with '[ie_name]'"""
self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg))
def report_extraction(self, id_or_name):
"""Report information extraction."""
self.to_screen(u'%s: Extracting information' % id_or_name)
def report_download_webpage(self, video_id):
"""Report webpage download."""
self.to_screen(u'%s: Downloading webpage' % video_id)
def report_age_confirmation(self):
"""Report attempt to confirm age."""
self.to_screen(u'Confirming age')
#Methods for following #608
#They set the correct value of the '_type' key
def video_result(self, video_info):
"""Returns a video"""
video_info['_type'] = 'video'
return video_info
def url_result(self, url, ie=None):
"""Returns a url that points to a page that should be processed"""
#TODO: ie should be the class used for getting the info
video_info = {'_type': 'url',
'url': url,
'ie_key': ie}
return video_info
def playlist_result(self, entries, playlist_id=None, playlist_title=None):
"""Returns a playlist"""
video_info = {'_type': 'playlist',
'entries': entries}
if playlist_id:
video_info['id'] = playlist_id
if playlist_title:
video_info['title'] = playlist_title
return video_info
class SearchInfoExtractor(InfoExtractor):
"""
Base class for paged search queries extractors.
They accept urls in the format _SEARCH_KEY(|all|[0-9]):{query}
Instances should define _SEARCH_KEY and _MAX_RESULTS.
"""
@classmethod
def _make_valid_url(cls):
return r'%s(?P<prefix>|[1-9][0-9]*|all):(?P<query>[\s\S]+)' % cls._SEARCH_KEY
@classmethod
def suitable(cls, url):
return re.match(cls._make_valid_url(), url) is not None
def _real_extract(self, query):
mobj = re.match(self._make_valid_url(), query)
if mobj is None:
raise ExtractorError(u'Invalid search query "%s"' % query)
prefix = mobj.group('prefix')
query = mobj.group('query')
if prefix == '':
return self._get_n_results(query, 1)
elif prefix == 'all':
return self._get_n_results(query, self._MAX_RESULTS)
else:
n = int(prefix)
if n <= 0:
raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query))
elif n > self._MAX_RESULTS:
self._downloader.report_warning(u'%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
n = self._MAX_RESULTS
return self._get_n_results(query, n)
def _get_n_results(self, query, n):
"""Get a specified number of results for a query"""
raise NotImplementedError("This method must be implemented by sublclasses")

727
youtube_dl/InfoExtractors/Youtube.py Normal file
View File

@ -0,0 +1,727 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import absolute_import
import netrc
import re
import socket
from ..utils import *
from .InfoExtractor import InfoExtractor
from .InfoExtractor import SearchInfoExtractor
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
_VALID_URL = r"""^
(
(?:https?://)? # http(s):// (optional)
(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
(?: # the various things that can precede the ID:
(?:(?:v|embed|e)/) # v/ or embed/ or e/
|(?: # or the v= param in all its forms
(?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
(?:\?|\#!?) # the params delimiter ? or # or #!
(?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
v=
)
)? # optional -> youtube.com/xxxx is OK
)? # all until now is optional -> you can pass the naked ID
([0-9A-Za-z_-]+) # here is it! the YouTube video ID
(?(1).+)? # if we found the ID, everything can follow
$"""
_LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
_NETRC_MACHINE = 'youtube'
# Listed in order of quality
_available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
_available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
_video_extensions = {
'13': '3gp',
'17': 'mp4',
'18': 'mp4',
'22': 'mp4',
'37': 'mp4',
'38': 'video', # You actually don't know if this will be MOV, AVI or whatever
'43': 'webm',
'44': 'webm',
'45': 'webm',
'46': 'webm',
}
_video_dimensions = {
'5': '240x400',
'6': '???',
'13': '???',
'17': '144x176',
'18': '360x640',
'22': '720x1280',
'34': '360x640',
'35': '480x854',
'37': '1080x1920',
'38': '3072x4096',
'43': '360x640',
'44': '480x854',
'45': '720x1280',
'46': '1080x1920',
}
IE_NAME = u'youtube'
@classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
if YoutubePlaylistIE.suitable(url): return False
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def report_lang(self):
"""Report attempt to set language."""
self.to_screen(u'Setting language')
def report_login(self):
"""Report attempt to log in."""
self.to_screen(u'Logging in')
def report_video_webpage_download(self, video_id):
"""Report attempt to download video webpage."""
self.to_screen(u'%s: Downloading video webpage' % video_id)
def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage."""
self.to_screen(u'%s: Downloading video info webpage' % video_id)
def report_video_subtitles_download(self, video_id):
"""Report attempt to download video info webpage."""
self.to_screen(u'%s: Checking available subtitles' % video_id)
def report_video_subtitles_request(self, video_id, sub_lang, format):
"""Report attempt to download video info webpage."""
self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format))
def report_video_subtitles_available(self, video_id, sub_lang_list):
"""Report available subtitles."""
sub_lang = ",".join(list(sub_lang_list.keys()))
self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang))
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
self.to_screen(u'%s: Extracting video information' % video_id)
def report_unavailable_format(self, video_id, format):
"""Report extracted video URL."""
self.to_screen(u'%s: Format %s not available' % (video_id, format))
def report_rtmp_download(self):
"""Indicate the download will use the RTMP protocol."""
self.to_screen(u'RTMP download detected')
def _get_available_subtitles(self, video_id):
self.report_video_subtitles_download(video_id)
request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
try:
sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
return (u'unable to download video subtitles: %s' % compat_str(err), None)
sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list)
if not sub_lang_list:
return (u'video doesn\'t have subtitles', None)
return sub_lang_list
def _list_available_subtitles(self, video_id):
sub_lang_list = self._get_available_subtitles(video_id)
self.report_video_subtitles_available(video_id, sub_lang_list)
def _request_subtitle(self, sub_lang, sub_name, video_id, format):
"""
Return tuple:
(error_message, sub_lang, sub)
"""
self.report_video_subtitles_request(video_id, sub_lang, format)
params = compat_urllib_parse.urlencode({
'lang': sub_lang,
'name': sub_name,
'v': video_id,
'fmt': format,
})
url = 'http://www.youtube.com/api/timedtext?' + params
try:
sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
return (u'unable to download video subtitles: %s' % compat_str(err), None, None)
if not sub:
return (u'Did not fetch video subtitles', None, None)
return (None, sub_lang, sub)
def _extract_subtitle(self, video_id):
"""
Return a list with a tuple:
[(error_message, sub_lang, sub)]
"""
sub_lang_list = self._get_available_subtitles(video_id)
sub_format = self._downloader.params.get('subtitlesformat')
if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
return [(sub_lang_list[0], None, None)]
if self._downloader.params.get('subtitleslang', False):
sub_lang = self._downloader.params.get('subtitleslang')
elif 'en' in sub_lang_list:
sub_lang = 'en'
else:
sub_lang = list(sub_lang_list.keys())[0]
if not sub_lang in sub_lang_list:
return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)]
subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
return [subtitle]
def _extract_all_subtitles(self, video_id):
sub_lang_list = self._get_available_subtitles(video_id)
sub_format = self._downloader.params.get('subtitlesformat')
if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
return [(sub_lang_list[0], None, None)]
subtitles = []
for sub_lang in sub_lang_list:
subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
subtitles.append(subtitle)
return subtitles
def _print_formats(self, formats):
print('Available formats:')
for x in formats:
print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')))
def _real_initialize(self):
if self._downloader is None:
return
username = None
password = None
downloader_params = self._downloader.params
# Attempt to use provided username and password or .netrc data
if downloader_params.get('username', None) is not None:
username = downloader_params['username']
password = downloader_params['password']
elif downloader_params.get('usenetrc', False):
try:
info = netrc.netrc().authenticators(self._NETRC_MACHINE)
if info is not None:
username = info[0]
password = info[2]
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError) as err:
self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
return
# Set language
request = compat_urllib_request.Request(self._LANG_URL)
try:
self.report_lang()
compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.report_warning(u'unable to set language: %s' % compat_str(err))
return
# No authentication to be performed
if username is None:
return
request = compat_urllib_request.Request(self._LOGIN_URL)
try:
login_page = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.report_warning(u'unable to fetch login page: %s' % compat_str(err))
return
galx = None
dsh = None
match = re.search(re.compile(r'<input.+?name="GALX".+?value="(.+?)"', re.DOTALL), login_page)
if match:
galx = match.group(1)
match = re.search(re.compile(r'<input.+?name="dsh".+?value="(.+?)"', re.DOTALL), login_page)
if match:
dsh = match.group(1)
# Log in
login_form_strs = {
u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
u'Email': username,
u'GALX': galx,
u'Passwd': password,
u'PersistentCookie': u'yes',
u'_utf8': u'霱',
u'bgresponse': u'js_disabled',
u'checkConnection': u'',
u'checkedDomains': u'youtube',
u'dnConn': u'',
u'dsh': dsh,
u'pstMsg': u'0',
u'rmShown': u'1',
u'secTok': u'',
u'signIn': u'Sign in',
u'timeStmp': u'',
u'service': u'youtube',
u'uilel': u'3',
u'hl': u'en_US',
}
# Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
# chokes on unicode
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
login_data = compat_urllib_parse.urlencode(login_form).encode('ascii')
request = compat_urllib_request.Request(self._LOGIN_URL, login_data)
try:
self.report_login()
login_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
self._downloader.report_warning(u'unable to log in: bad username or password')
return
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
return
# Confirm age
age_form = {
'next_url': '/',
'action_confirm': 'Confirm',
}
request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form))
try:
self.report_age_confirmation()
age_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
def _extract_id(self, url):
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(2)
return video_id
def _real_extract(self, url):
# Extract original video URL from URL with redirection, like age verification, using next_url parameter
mobj = re.search(self._NEXT_URL_RE, url)
if mobj:
url = 'https://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
video_id = self._extract_id(url)
# Get video webpage
self.report_video_webpage_download(video_id)
url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
request = compat_urllib_request.Request(url)
try:
video_webpage_bytes = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
raise ExtractorError(u'Unable to download video webpage: %s' % compat_str(err))
video_webpage = video_webpage_bytes.decode('utf-8', 'ignore')
# Attempt to extract SWF player URL
mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
if mobj is not None:
player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
else:
player_url = None
# Get video info
self.report_video_info_webpage_download(video_id)
for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
video_info_url = ('https://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
% (video_id, el_type))
video_info_webpage = self._download_webpage(video_info_url, video_id,
note=False,
errnote='unable to download video info webpage')
video_info = compat_parse_qs(video_info_webpage)
if 'token' in video_info:
break
if 'token' not in video_info:
if 'reason' in video_info:
raise ExtractorError(u'YouTube said: %s' % video_info['reason'][0])
else:
raise ExtractorError(u'"token" parameter not in video info for unknown reason')
# Check for "rental" videos
if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
raise ExtractorError(u'"rental" videos not supported')
# Start extracting information
self.report_information_extraction(video_id)
# uploader
if 'author' not in video_info:
raise ExtractorError(u'Unable to extract uploader name')
video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0])
# uploader_id
video_uploader_id = None
mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage)
if mobj is not None:
video_uploader_id = mobj.group(1)
else:
self._downloader.report_warning(u'unable to extract uploader nickname')
# title
if 'title' not in video_info:
raise ExtractorError(u'Unable to extract video title')
video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
# thumbnail image
if 'thumbnail_url' not in video_info:
self._downloader.report_warning(u'unable to extract video thumbnail')
video_thumbnail = ''
else: # don't panic if we can't find it
video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
# upload date
upload_date = None
mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
if mobj is not None:
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
upload_date = unified_strdate(upload_date)
# description
video_description = get_element_by_id("eow-description", video_webpage)
if video_description:
video_description = clean_html(video_description)
else:
fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
if fd_mobj:
video_description = unescapeHTML(fd_mobj.group(1))
else:
video_description = u''
# subtitles
video_subtitles = None
if self._downloader.params.get('writesubtitles', False):
video_subtitles = self._extract_subtitle(video_id)
if video_subtitles:
(sub_error, sub_lang, sub) = video_subtitles[0]
if sub_error:
self._downloader.report_error(sub_error)
if self._downloader.params.get('allsubtitles', False):
video_subtitles = self._extract_all_subtitles(video_id)
for video_subtitle in video_subtitles:
(sub_error, sub_lang, sub) = video_subtitle
if sub_error:
self._downloader.report_error(sub_error)
if self._downloader.params.get('listsubtitles', False):
sub_lang_list = self._list_available_subtitles(video_id)
return
if 'length_seconds' not in video_info:
self._downloader.report_warning(u'unable to extract video duration')
video_duration = ''
else:
video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
# token
video_token = compat_urllib_parse.unquote_plus(video_info['token'][0])
# Decide which formats to download
req_format = self._downloader.params.get('format', None)
if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
self.report_rtmp_download()
video_url_list = [(None, video_info['conn'][0])]
elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
url_map = {}
for url_data_str in video_info['url_encoded_fmt_stream_map'][0].split(','):
url_data = compat_parse_qs(url_data_str)
if 'itag' in url_data and 'url' in url_data:
url = url_data['url'][0] + '&signature=' + url_data['sig'][0]
if not 'ratebypass' in url: url += '&ratebypass=yes'
url_map[url_data['itag'][0]] = url
format_limit = self._downloader.params.get('format_limit', None)
available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
if format_limit is not None and format_limit in available_formats:
format_list = available_formats[available_formats.index(format_limit):]
else:
format_list = available_formats
existing_formats = [x for x in format_list if x in url_map]
if len(existing_formats) == 0:
raise ExtractorError(u'no known formats available for video')
if self._downloader.params.get('listformats', None):
self._print_formats(existing_formats)
return
if req_format is None or req_format == 'best':
video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
elif req_format == 'worst':
video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
elif req_format in ('-1', 'all'):
video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
else:
# Specific formats. We pick the first in a slash-delimeted sequence.
# For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'.
req_formats = req_format.split('/')
video_url_list = None
for rf in req_formats:
if rf in url_map:
video_url_list = [(rf, url_map[rf])]
break
if video_url_list is None:
raise ExtractorError(u'requested format not available')
else:
raise ExtractorError(u'no conn or url_encoded_fmt_stream_map information found in video info')
results = []
for format_param, video_real_url in video_url_list:
# Extension
video_extension = self._video_extensions.get(format_param, 'flv')
video_format = '{0} - {1}'.format(format_param if format_param else video_extension,
self._video_dimensions.get(format_param, '???'))
results.append({
'id': video_id,
'url': video_real_url,
'uploader': video_uploader,
'uploader_id': video_uploader_id,
'upload_date': upload_date,
'title': video_title,
'ext': video_extension,
'format': video_format,
'thumbnail': video_thumbnail,
'description': video_description,
'player_url': player_url,
'subtitles': video_subtitles,
'duration': video_duration
})
return results
class YoutubeSearchIE(SearchInfoExtractor):
"""Information Extractor for YouTube search queries."""
_API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
_MAX_RESULTS = 1000
IE_NAME = u'youtube:search'
_SEARCH_KEY = 'ytsearch'
def report_download_page(self, query, pagenum):
"""Report attempt to download search page with given number."""
query = query.decode(preferredencoding())
self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
def _get_n_results(self, query, n):
"""Get a specified number of results for a query"""
video_ids = []
pagenum = 0
limit = n
while (50 * pagenum) < limit:
self.report_download_page(query, pagenum+1)
result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1)
request = compat_urllib_request.Request(result_url)
try:
data = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
raise ExtractorError(u'Unable to download API page: %s' % compat_str(err))
api_response = json.loads(data)['data']
if not 'items' in api_response:
raise ExtractorError(u'[youtube] No video results')
new_ids = list(video['id'] for video in api_response['items'])
video_ids += new_ids
limit = min(n, api_response['totalItems'])
pagenum += 1
if len(video_ids) > n:
video_ids = video_ids[:n]
videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids]
return self.playlist_result(videos, query)
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
_VALID_URL = r"""(?:
(?:https?://)?
(?:\w+\.)?
youtube\.com/
(?:
(?:course|view_play_list|my_playlists|artist|playlist|watch)
\? (?:.*?&)*? (?:p|a|list)=
| p/
)
((?:PL|EC|UU)?[0-9A-Za-z-_]{10,})
.*
|
((?:PL|EC|UU)[0-9A-Za-z-_]{10,})
)"""
_TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/playlists/%s?max-results=%i&start-index=%i&v=2&alt=json'
_MAX_RESULTS = 50
IE_NAME = u'youtube:playlist'
@classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def _real_extract(self, url):
# Extract playlist id
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
# Download playlist videos from API
playlist_id = mobj.group(1) or mobj.group(2)
page_num = 1
videos = []
while True:
url = self._TEMPLATE_URL % (playlist_id, self._MAX_RESULTS, self._MAX_RESULTS * (page_num - 1) + 1)
page = self._download_webpage(url, playlist_id, u'Downloading page #%s' % page_num)
try:
response = json.loads(page)
except ValueError as err:
raise ExtractorError(u'Invalid JSON in API response: ' + compat_str(err))
if 'feed' not in response:
raise ExtractorError(u'Got a malformed response from YouTube API')
playlist_title = response['feed']['title']['$t']
if 'entry' not in response['feed']:
# Number of videos is a multiple of self._MAX_RESULTS
break
videos += [ (entry['yt$position']['$t'], entry['content']['src'])
for entry in response['feed']['entry']
if 'content' in entry ]
if len(response['feed']['entry']) < self._MAX_RESULTS:
break
page_num += 1
videos = [v[1] for v in sorted(videos)]
url_results = [self.url_result(url, 'Youtube') for url in videos]
return [self.playlist_result(url_results, playlist_id, playlist_title)]
class YoutubeChannelIE(InfoExtractor):
"""Information Extractor for YouTube channels."""
_VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)"
_TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
_MORE_PAGES_INDICATOR = 'yt-uix-load-more'
_MORE_PAGES_URL = 'http://www.youtube.com/channel_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s'
IE_NAME = u'youtube:channel'
def extract_videos_from_page(self, page):
ids_in_page = []
for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&?', page):
if mobj.group(1) not in ids_in_page:
ids_in_page.append(mobj.group(1))
return ids_in_page
def _real_extract(self, url):
# Extract channel id
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
# Download channel page
channel_id = mobj.group(1)
video_ids = []
pagenum = 1
url = self._TEMPLATE_URL % (channel_id, pagenum)
page = self._download_webpage(url, channel_id,
u'Downloading page #%s' % pagenum)
# Extract video identifiers
ids_in_page = self.extract_videos_from_page(page)
video_ids.extend(ids_in_page)
# Download any subsequent channel pages using the json-based channel_ajax query
if self._MORE_PAGES_INDICATOR in page:
while True:
pagenum = pagenum + 1
url = self._MORE_PAGES_URL % (pagenum, channel_id)
page = self._download_webpage(url, channel_id,
u'Downloading page #%s' % pagenum)
page = json.loads(page)
ids_in_page = self.extract_videos_from_page(page['content_html'])
video_ids.extend(ids_in_page)
if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']:
break
self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids)))
urls = ['http://www.youtube.com/watch?v=%s' % id for id in video_ids]
url_entries = [self.url_result(url, 'Youtube') for url in urls]
return [self.playlist_result(url_entries, channel_id)]
class YoutubeUserIE(InfoExtractor):
"""Information Extractor for YouTube users."""
_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
_GDATA_PAGE_SIZE = 50
_GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'
IE_NAME = u'youtube:user'
def _real_extract(self, url):
# Extract username
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
username = mobj.group(1)
# Download video ids using YouTube Data API. Result size per
# query is limited (currently to 50 videos) so we need to query
# page by page until there are no video ids - it means we got
# all of them.
video_ids = []
pagenum = 0
while True:
start_index = pagenum * self._GDATA_PAGE_SIZE + 1
gdata_url = self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)
page = self._download_webpage(gdata_url, username,
u'Downloading video ids from %d to %d' % (start_index, start_index + self._GDATA_PAGE_SIZE))
# Extract video identifiers
ids_in_page = []
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
if mobj.group(1) not in ids_in_page:
ids_in_page.append(mobj.group(1))
video_ids.extend(ids_in_page)
# A little optimization - if current page is not
# "full", ie. does not contain PAGE_SIZE video ids then
# we can assume that this page is the last one - there
# are no more ids on further pages - no need to query
# again.
if len(ids_in_page) < self._GDATA_PAGE_SIZE:
break
pagenum += 1
urls = ['http://www.youtube.com/watch?v=%s' % video_id for video_id in video_ids]
url_results = [self.url_result(url, 'Youtube') for url in urls]
return [self.playlist_result(url_results, playlist_title = username)]

28
youtube_dl/InfoExtractors/__init__.py Executable file
View File

@ -0,0 +1,28 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import absolute_import
IEs = [
('Youtube', ['YoutubePlaylistIE', 'YoutubeChannelIE',
'YoutubeUserIE', 'YoutubeSearchIE', 'YoutubeIE']),
('Generic', ['GenericIE']),
]
IE_list = []
for module, IE_names in IEs:
_mod = __import__('youtube_dl.InfoExtractors.' + module,
globals(), locals(), IE_names)
for IE_name in IE_names:
IE_list.append(getattr(_mod, IE_name))
def gen_extractors():
""" Return a list of an instance of every supported extractor """
return [ IE() for IE in IE_list ]
def get_info_extractor(IE_name):
"""Returns the info extractor class with the given ie_name"""
return next(IE for IE in IE_list if IE.__name__ == IE_name + 'IE')