Merge remote-tracking branch 'upstream/master' into upstream

.gitignore

@@ -1,9 +1,10 @@
 /build/
 /dist/
-/*.egg-info/
+/MANIFEST
+*.egg-info/
+*.py[cod]
 
 _*/
-*.py[cod]
 
 *.download
 *.cmt.*

.travis.yml

@@ -0,0 +1,6 @@
+# https://travis-ci.org/soimort/you-get
+language: python
+python:
+  - "3.2"
+  - "3.3"
+script: make test

CHANGELOG.txt

@@ -1,6 +1,32 @@
 Changelog
 =========
 
+0.3.1
+-----
+
+*Date: 2013-02-15*
+
+* Fix issues for Google+ and Mixcloud.
+* API changed.
+
+0.3.0
+-----
+
+*Date: 2013-02-08*
+
+* Add support for:
+    - Niconico
+
+0.3dev-20130201
+---------------
+
+*Date: 2013-02-01*
+
+* Add support for:
+    - Mixcloud
+    - Facebook
+    - Joy.cn
+
 0.3dev-20130125
 ---------------
 

MANIFEST

@@ -1,21 +0,0 @@
-# file GENERATED by distutils, do NOT edit
-CHANGELOG.txt
-LICENSE.txt
-Makefile
-README.md
-README.txt
-setup.cfg
-setup.py
-you-get
-you-get.json
-you_get/__init__.py
-you_get/common.py
-you_get/main.py
-you_get/downloader/__init__.py
-you_get/downloader/tudou.py
-you_get/downloader/yinyuetai.py
-you_get/downloader/youku.py
-you_get/downloader/youtube.py
-you_get/processor/__init__.py
-you_get/processor/merge_flv.py
-you_get/processor/merge_mp4.py

Makefile

@@ -2,13 +2,21 @@ SETUP = python3 setup.py
 
 .PHONY: default clean build sdist bdist bdist_egg install release
 
-default: build sdist bdist bdist_egg
+default: i
+
+i:
+	@(cd src/; python -i -c 'import you_get; print("You-Get %s (%s)\n>>> import you_get" % (you_get.__version__, you_get.__date__))')
+
+test:
+	$(SETUP) test
 
 clean:
 	zenity --question
-	rm -fr build/ dist/ *.egg-info/
+	rm -fr build/ dist/ src/*.egg-info/
 	find . | grep __pycache__ | xargs rm -fr
 
+all: build sdist bdist bdist_egg
+
 build:
 	$(SETUP) build
 

README.md

@@ -1,11 +1,13 @@
 # You-Get
 
-[You-Get](https://github.com/soimort/you-get) is a video downloader runs on Python 3. It aims at easing the download of videos on [YouTube](http://www.youtube.com), [Youku](http://www.youku.com)/[Tudou](http://www.tudou.com) (biggest online video providers in China), etc., in one script.
+[You-Get](https://github.com/soimort/you-get) is a video downloader runs on Python 3. It aims at easing the download of videos on [YouTube](http://www.youtube.com), [Youku](http://www.youku.com)/[Tudou](http://www.tudou.com) (biggest online video providers in China), [ Niconico](http://www.nicovideo.jp), etc., in one script.
 
 See the project homepage <http://www.soimort.org/you-get> for further documentation.
 
 Fork me on GitHub: <https://github.com/soimort/you-get>
 
+[![Build Status](https://api.travis-ci.org/soimort/you-get.png)](https://travis-ci.org/soimort/you-get)
+
 ## Features
 
 ### Supported Sites (As of Now)
@@ -17,6 +19,8 @@ Fork me on GitHub: <https://github.com/soimort/you-get>
 * Google+ <http://plus.google.com>
 * Tumblr <http://www.tumblr.com>
 * SoundCloud <http://soundcloud.com>
+* Mixcloud <http://www.mixcloud.com>
+* Niconico (ニコニコ動画) <http://www.nicovideo.jp>
 * Youku (优酷) <http://www.youku.com>
 * Tudou (土豆) <http://www.tudou.com>
 * YinYueTai (音悦台) <http://www.yinyuetai.com>
@@ -148,17 +152,14 @@ For a complete list of all available options, see:
 
 In Python 3 (interactive):
 
-    >>> import you_get
-    
-    >>> you_get.__version__
-    '0.2'
-    
-    >>> you_get.youtube_download("http://www.youtube.com/watch?v=8bQlxQJEzLk", info_only = True)
+    >>> from you_get.downloader import *
+    >>> youtube.download("http://www.youtube.com/watch?v=8bQlxQJEzLk", info_only = True)
     Video Site: YouTube.com
     Title:      If you're good at something, never do it for free!
     Type:       WebM video (video/webm)
     Size:       0.13 MB (133176 Bytes)
     
+    >>> import you_get
     >>> you_get.any_download("http://www.youtube.com/watch?v=sGwy8DsUJ4M")
     Video Site: YouTube.com
     Title:      Mort from Madagascar LIKES
@@ -211,6 +212,8 @@ You-Get基于优酷下载脚本[iambus/youku-lixian](https://github.com/iambus/y
 * Google+ <http://plus.google.com>
 * Tumblr <http://www.tumblr.com>
 * SoundCloud <http://soundcloud.com>
+* Mixcloud <http://www.mixcloud.com>
+* NICONICO动画 <http://www.nicovideo.jp>
 * 优酷 <http://www.youku.com>
 * 土豆 <http://www.tudou.com>
 * 音悦台 <http://www.yinyuetai.com>

README.txt

@@ -1,7 +1,7 @@
 You-Get
 =======
 
-`You-Get <https://github.com/soimort/you-get>`_ is a video downloader runs on Python 3. It aims at easing the download of videos on `YouTube <http://www.youtube.com>`_, `Youku <http://www.youku.com>`_/`Tudou <http://www.tudou.com>`_ (biggest online video providers in China), etc., in one script.
+`You-Get <https://github.com/soimort/you-get>`_ is a video downloader runs on Python 3. It aims at easing the download of videos on `YouTube <http://www.youtube.com>`_, `Youku <http://www.youku.com>`_/`Tudou <http://www.tudou.com>`_ (biggest online video providers in China), `Niconico <http://www.nicovideo.jp>`_, etc., in one script.
 
 See the project homepage http://www.soimort.org/you-get for further documentation.
 
@@ -20,6 +20,8 @@ Supported Sites (As of Now)
 * Google+ http://plus.google.com
 * Tumblr http://www.tumblr.com
 * SoundCloud http://soundcloud.com
+* Mixcloud http://www.mixcloud.com
+* Niconico (ニコニコ動画) http://www.nicovideo.jp
 * Youku (优酷) http://www.youku.com
 * Tudou (土豆) http://www.tudou.com
 * YinYueTai (音悦台) http://www.yinyuetai.com
@@ -156,17 +158,14 @@ Examples (For Developers)
 
 In Python 3 (interactive)::
 
-    >>> import you_get
-    
-    >>> you_get.__version__
-    '0.2'
-    
-    >>> you_get.youtube_download("http://www.youtube.com/watch?v=8bQlxQJEzLk", info_only = True)
+    >>> from you_get.downloader import *
+    >>> youtube.download("http://www.youtube.com/watch?v=8bQlxQJEzLk", info_only = True)
     Video Site: YouTube.com
     Title:      If you're good at something, never do it for free!
     Type:       WebM video (video/webm)
     Size:       0.13 MB (133176 Bytes)
     
+    >>> import you_get
     >>> you_get.any_download("http://www.youtube.com/watch?v=sGwy8DsUJ4M")
     Video Site: YouTube.com
     Title:      Mort from Madagascar LIKES

setup.py

@@ -1,13 +1,16 @@
 #!/usr/bin/env python3
 
-PROJ_METADATA = 'you-get.json'
+PROJ_NAME = 'you-get'
+PACKAGE_NAME = 'you_get'
+
+PROJ_METADATA = '%s.json' % PROJ_NAME
 
 import os, json, imp
 here = os.path.abspath(os.path.dirname(__file__))
 proj_info = json.loads(open(os.path.join(here, PROJ_METADATA)).read())
 README = open(os.path.join(here, 'README.txt')).read()
 CHANGELOG = open(os.path.join(here, 'CHANGELOG.txt')).read()
-VERSION = imp.load_source('version', os.path.join(here, 'you_get/version.py')).__version__
+VERSION = imp.load_source('version', os.path.join(here, 'src/%s/version.py' % PACKAGE_NAME)).__version__
 
 from setuptools import setup, find_packages
 setup(
@@ -24,7 +27,10 @@ setup(
     
     long_description = README + '\n\n' + CHANGELOG,
     
-    packages = find_packages(),
+    packages = find_packages('src'),
+    package_dir = {'' : 'src'},
+    
+    test_suite = 'tests',
     
     platforms = 'any',
     zip_safe = False,

src/you_get/__init__.py

@@ -0,0 +1,9 @@
+#!/usr/bin/env python
+
+from .processor import *
+
+from .downloader import *
+
+from .version import *
+from .common import *
+from .__main__ import *

src/you_get/__main__.py

@@ -32,6 +32,8 @@ def url_to_module(url):
         'joy': joy,
         'kankanews': bilibili,
         'ku6': ku6,
+        'mixcloud': mixcloud,
+        'nicovideo': nicovideo,
         'pptv': pptv,
         'qq': qq,
         'sina': sina,
@@ -63,3 +65,6 @@ def any_download_playlist(url, output_dir = '.', merge = True, info_only = False
 
 def main():
     script_main('you-get', any_download, any_download_playlist)
+
+if __name__ == "__main__":
+    main()

src/you_get/common.py

@@ -18,7 +18,7 @@ fake_headers = {
     'Accept-Charset': 'UTF-8,*;q=0.5',
     'Accept-Encoding': 'gzip,deflate,sdch',
     'Accept-Language': 'en-US,en;q=0.8',
-    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.57 Safari/537.1'
+    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:13.0) Gecko/20100101 Firefox/13.0'
 }
 
 if sys.stdout.isatty():
@@ -132,9 +132,20 @@ def url_info(url, faker = False):
     if type in mapping:
         ext = mapping[type]
     else:
-        ext = None
+        type = None
+        if headers['content-disposition']:
+            filename = parse.unquote(r1(r'filename="?(.+)"?', headers['content-disposition']))
+            if len(filename.split('.')) > 1:
+                ext = filename.split('.')[-1]
+            else:
+                ext = None
+        else:
+            ext = None
     
-    size = int(headers['content-length'])
+    if headers['transfer-encoding'] != 'chunked':
+        size = int(headers['content-length'])
+    else:
+        size = None
     
     return type, ext, size
 
@@ -357,7 +368,6 @@ def download_urls(urls, title, ext, total_size, output_dir = '.', refer = None,
         print('Real URLs:\n', urls, '\n')
         return
     
-    #assert ext in ('3gp', 'flv', 'mp4', 'webm')
     if not total_size:
         try:
             total_size = urls_size(urls)
@@ -506,7 +516,7 @@ def playlist_not_supported(name):
 def print_info(site_info, title, type, size):
     if type in ['3gp']:
         type = 'video/3gpp'
-    elif type in ['asf']:
+    elif type in ['asf', 'wmv']:
         type = 'video/x-ms-asf'
     elif type in ['flv', 'f4v']:
         type = 'video/x-flv'
@@ -646,7 +656,7 @@ def script_main(script_name, download, download_playlist = None):
             sys.exit(1)
     if not args:
         print(help)
-        sys.exit(1)
+        sys.exit()
     
     set_http_proxy(proxy)
     

src/you_get/downloader/__init__.py

@@ -10,7 +10,9 @@ from .ifeng import *
 from .iqiyi import *
 from .joy import *
 from .ku6 import *
+from .mixcloud import *
 from .netease import *
+from .nicovideo import *
 from .pptv import *
 from .qq import *
 from .sina import *

src/you_get/downloader/facebook.py

@@ -10,7 +10,7 @@ def facebook_download(url, output_dir = '.', merge = True, info_only = False):
     title = r1(r'<title id="pageTitle">(.+) \| Facebook</title>', html)
     
     for fmt in ["hd_src", "sd_src"]:
-        src = parse.unquote(unicodize(r1(r'\["' + fmt + '","([^"]*)', html)))
+        src= re.sub(r'\\/', r'/', r1(r'"' + fmt + '":"([^"]*)"', parse.unquote(unicodize(r1(r'\["params","([^"]*)"\]', html)))))
         if src:
             break
     

src/you_get/downloader/googleplus.py

@@ -0,0 +1,62 @@
+#!/usr/bin/env python
+
+__all__ = ['googleplus_download']
+
+from ..common import *
+
+import re
+
+def googleplus_download(url, output_dir = '.', merge = True, info_only = False):
+    # Percent-encoding Unicode URL
+    url = parse.quote(url, safe = ':/+%')
+    
+    html = get_html(url)
+    html = parse.unquote(html).replace('\/', '/')
+    
+    title = r1(r'<meta property="og:title" content="([^"]*)"', html) or r1(r'<title>(.*)</title>', html) or r1(r'<title>(.*)\n', html)
+    
+    url2 = r1(r'<a href="([^"]+)" target="_blank" class="Mn" >', html)
+    if url2:
+        html = get_html(url2)
+        html = parse.unquote(html.replace('\/', '/'))
+    
+    real_url = unicodize(r1(r'"(https://video.googleusercontent.com/[^"]*)",1\]', html).replace('\/', '/'))
+    if real_url:
+        type, ext, size = url_info(real_url)
+    if not real_url or not size:
+        url_data = re.findall(r'(\[[^\[\"]+\"http://redirector.googlevideo.com/.*\"\])', html)
+        for itag in [
+            '38',
+            '46', '37',
+            '102', '45', '22',
+            '84',
+            '120',
+            '85',
+            '44', '35',
+            '101', '100', '43', '34', '82', '18',
+            '6',
+            '83', '5', '36',
+            '17',
+            '13',
+        ]:
+            real_url = None
+            for url_item in url_data:
+                if itag == str(eval(url_item)[0]):
+                    real_url = eval(url_item)[3]
+                    break
+            if real_url:
+                break
+        real_url = unicodize(real_url)
+    
+        type, ext, size = url_info(real_url)
+    
+    if not ext:
+        ext = 'mp4'
+    
+    print_info(site_info, title, ext, size)
+    if not info_only:
+        download_urls([real_url], title, ext, size, output_dir, merge = merge)
+
+site_info = "plus.google.com"
+download = googleplus_download
+download_playlist = playlist_not_supported('googleplus')

src/you_get/downloader/mixcloud.py

@@ -0,0 +1,28 @@
+#!/usr/bin/env python
+
+__all__ = ['mixcloud_download']
+
+from ..common import *
+
+def mixcloud_download(url, output_dir = '.', merge = True, info_only = False):
+    html = get_html(url)
+    title = r1(r'<meta property="og:title" content="([^"]*)"', html)
+    url = r1("data-preview-url=\"([^\"]+)\"", html)
+    
+    url = re.sub(r'previews', r'cloudcasts/originals', url)
+    for i in range(10, 30):
+        url = re.sub(r'stream[^.]*', r'stream' + str(i), url)
+        
+        try:
+            type, ext, size = url_info(url)
+            break
+        except:
+            continue
+    
+    print_info(site_info, title, type, size)
+    if not info_only:
+        download_urls([url], title, ext, size, output_dir, merge = merge)
+
+site_info = "Mixcloud.com"
+download = mixcloud_download
+download_playlist = playlist_not_supported('mixcloud')

src/you_get/downloader/nicovideo.py

@@ -0,0 +1,39 @@
+#!/usr/bin/env python
+
+__all__ = ['nicovideo_download']
+
+from ..common import *
+
+def nicovideo_login(user, password):
+    data = "current_form=login&mail=" + user +"&password=" + password + "&login_submit=Log+In"
+    response = request.urlopen(request.Request("https://secure.nicovideo.jp/secure/login?site=niconico", headers = fake_headers, data = data.encode('utf-8')))
+    return response.headers
+
+def nicovideo_download(url, output_dir = '.', merge = True, info_only = False):
+    request.install_opener(request.build_opener(request.HTTPCookieProcessor()))
+    
+    import netrc, getpass
+    info = netrc.netrc().authenticators('nicovideo')
+    if info is None:
+        user = input("User:     ")
+        password = getpass.getpass("Password: ")
+    else:
+        user, password = info[0], info[2]
+    print("Logging in...")
+    nicovideo_login(user, password)
+    
+    html = get_html(url) # necessary!
+    title = unicodize(r1(r'title:\s*\'(.*)\',', html))
+    
+    api_html = get_html('http://www.nicovideo.jp/api/getflv?v=%s' % url.split('/')[-1])
+    real_url = parse.unquote(r1(r'url=([^&]+)&', api_html))
+    
+    type, ext, size = url_info(real_url)
+    
+    print_info(site_info, title, type, size)
+    if not info_only:
+        download_urls([real_url], title, ext, size, output_dir, merge = merge)
+
+site_info = "Nicovideo.jp"
+download = nicovideo_download
+download_playlist = playlist_not_supported('nicovideo')

src/you_get/version.py

@@ -0,0 +1,6 @@
+#!/usr/bin/env python
+
+__all__ = ['__version__', '__date__']
+
+__version__ = '0.3.1'
+__date__ = '2013-02-15'

tests/test.py

@@ -0,0 +1,32 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import unittest
+
+from you_get import *
+from you_get.__main__ import url_to_module
+
+class YouGetTests(unittest.TestCase):
+    
+    def test_googleplus(self):
+        for url in [ 
+            "http://plus.google.com/111438309227794971277/posts/So6bW37WWtp",
+            "http://plus.google.com/114038303885145553998/posts/7Jkwa35HZu8",
+            "http://plus.google.com/109544372058574620997/posts/Hn9P3Mbuyud",
+            "http://plus.google.com/photos/109544372058574620997/albums/5835145047890484737/5835145057636064194",
+            "http://plus.google.com/102663035987142737445/posts/jJRu43KQFT5",
+            "http://plus.google.com/+%E5%B9%B3%E7%94%B0%E6%A2%A8%E5%A5%88/posts/jJRu43KQFT5",
+            "http://plus.google.com/+平田梨奈/posts/jJRu43KQFT5",
+            "http://plus.google.com/photos/102663035987142737445/albums/5844078581209509505/5844078587839097874",
+            "http://plus.google.com/photos/+%E5%B9%B3%E7%94%B0%E6%A2%A8%E5%A5%88/albums/5844078581209509505/5844078587839097874",
+            "http://plus.google.com/photos/+平田梨奈/albums/5844078581209509505/5844078587839097874",
+        ]:
+            url_to_module(url).download(url, info_only = True)
+        
+    def test_mixcloud(self):
+        for url in [ 
+            "http://www.mixcloud.com/beatbopz/beat-bopz-disco-mix/",
+            "http://www.mixcloud.com/beatbopz/tokyo-taste-vol4/",
+            "http://www.mixcloud.com/DJVadim/north-america-are-you-ready/",
+        ]:
+            url_to_module(url).download(url, info_only = True)

you-get

@@ -1,5 +1,8 @@
 #!/usr/bin/env python3
 
+import os, sys
+sys.path.insert(0, os.path.join((os.path.dirname(os.path.abspath(__file__))), "src"))
+
 from you_get import *
 
 if __name__ == "__main__":

you-get.json

@@ -5,8 +5,8 @@
     "url": "http://www.soimort.org/you-get/",
     "license": "MIT",
     
-    "description": "A YouTube/Youku video downloader written in Python 3.",
-    "keywords": "video download youtube youku",
+    "description": "A YouTube/Youku/Niconico video downloader written in Python 3.",
+    "keywords": "video download youtube youku niconico",
     
     "classifiers": [
         "Development Status :: 2 - Pre-Alpha",
@@ -31,6 +31,6 @@
         ],
     
     "console_scripts": [
-        "you-get = you_get.main:main"
+        "you-get = you_get.__main__:main"
         ]
 }

you_get/__init__.py

@@ -1,8 +0,0 @@
-#!/usr/bin/env python
-
-from .processor import *
-from .downloader import *
-
-from .version import __version__, __date__
-from .common import script_main
-from .main import *

you_get/downloader/googleplus.py

@@ -1,56 +0,0 @@
-#!/usr/bin/env python
-
-__all__ = ['googleplus_download']
-
-from ..common import *
-
-import re
-
-def googleplus_download(url, output_dir = '.', merge = True, info_only = False):
-    # Percent-encoding Unicode URL
-    url = parse.quote(url, safe = ':/+%')
-    
-    html = get_html(url)
-    html = parse.unquote(html).replace('\/', '/')
-    
-    title = r1(r'<title>(.*)</title>', html) or r1(r'<title>(.*)\n', html)
-    
-    url2 = r1(r'"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]', html)
-    if url2:
-        html = get_html(url2)
-        html = parse.unquote(html.replace('\/', '/'))
-    
-    url_data = re.findall(r'(\[[^\[\"]+\"http://redirector.googlevideo.com/.*\"\])', html)
-    
-    for itag in [
-        '38',
-        '46', '37',
-        '102', '45', '22',
-        '84',
-        '120',
-        '85',
-        '44', '35',
-        '101', '100', '43', '34', '82', '18',
-        '6',
-        '83', '5', '36',
-        '17',
-        '13',
-    ]:
-        real_url = None
-        for url_item in url_data:
-            if itag == str(eval(url_item)[0]):
-                real_url = eval(url_item)[3]
-                break
-        if real_url:
-            break
-    real_url = unicodize(real_url)
-    
-    type, ext, size = url_info(real_url)
-    
-    print_info(site_info, title, type, size)
-    if not info_only:
-        download_urls([real_url], title, ext, size, output_dir, merge = merge)
-
-site_info = "plus.google.com"
-download = googleplus_download
-download_playlist = playlist_not_supported('googleplus')

you_get/version.py

@@ -1,4 +0,0 @@
-#!/usr/bin/env python
-
-__version__ = '0.3dev-20130125'
-__date__ = '2013-01-25'