[break] adapt to new paths
authorPhilipp Hagemeister <phihag@phihag.de>
Sun, 23 Jun 2013 20:59:51 +0000 (22:59 +0200)
committerPhilipp Hagemeister <phihag@phihag.de>
Sun, 23 Jun 2013 20:59:51 +0000 (22:59 +0200)
1  2 
test/tests.json
youtube_dl/extractor/__init__.py
youtube_dl/extractor/breakcom.py

diff --cc test/tests.json
index 86dc48570ae61ed01e753c287d01806ef4824ead,30ab11fd83a19197ab889c50e87d04fe883d8982..01367b0fb44c60917db9c50a4ab05a7ddb1a6cdd
      "file": "484091715184808010_284179915.mp4",
      "md5": "deda4ff333abe2e118740321e992605b",
      "info_dict": {
 -        "uploader": "videoseconds",
 +        "uploader_id": "videoseconds",
          "title": "Instagram photo by @videoseconds (Videos)"
      }
+   },
+   {
+     "name": "Break",
+     "url": "http://www.break.com/video/when-girls-act-like-guys-2468056",
+     "file": "2468056.mp4",
+     "md5": "a3513fb1547fba4fb6cfac1bffc6c46b",
+     "info_dict": {
+         "title": "When Girls Act Like D-Bags"
+     }
    }
  ]
index 4729512edde28f7caf180cc48975bed0cf23c899,0000000000000000000000000000000000000000..b208f9002e9e9bb31771b12e6b96399859d1382f
mode 100644,000000..100644
--- /dev/null
@@@ -1,131 -1,0 +1,133 @@@
 +
 +from .ard import ARDIE
 +from .arte import ArteTvIE
 +from .bandcamp import BandcampIE
 +from .bliptv import BlipTVIE, BlipTVUserIE
++from .breakcom import BreakIE
 +from .comedycentral import ComedyCentralIE
 +from .collegehumor import CollegeHumorIE
 +from .dailymotion import DailymotionIE
 +from .depositfiles import DepositFilesIE
 +from .eighttracks import EightTracksIE
 +from .escapist import EscapistIE
 +from .facebook import FacebookIE
 +from .flickr import FlickrIE
 +from .funnyordie import FunnyOrDieIE
 +from .gametrailers import GametrailersIE
 +from .generic import GenericIE
 +from .googleplus import GooglePlusIE
 +from .googlesearch import GoogleSearchIE
 +from .howcast import HowcastIE
 +from .hypem import HypemIE
 +from .ina import InaIE
 +from .infoq import InfoQIE
 +from .justintv import JustinTVIE
 +from .keek import KeekIE
 +from .liveleak import LiveLeakIE
 +from .metacafe import MetacafeIE
 +from .mixcloud import MixcloudIE
 +from .mtv import MTVIE
 +from .myspass import MySpassIE
 +from .myvideo import MyVideoIE
 +from .nba import NBAIE
 +from .statigram import StatigramIE
 +from .photobucket import PhotobucketIE
 +from .pornotube import PornotubeIE
 +from .rbmaradio import RBMARadioIE
 +from .redtube import RedTubeIE
 +from .soundcloud import SoundcloudIE, SoundcloudSetIE
 +from .spiegel import SpiegelIE
 +from .stanfordoc import StanfordOpenClassroomIE
 +from .steam import SteamIE
 +from .teamcoco import TeamcocoIE
 +from .ted import TEDIE
 +from .tumblr import TumblrIE
 +from .ustream import UstreamIE
 +from .vbox7 import Vbox7IE
 +from .vimeo import VimeoIE
 +from .vine import VineIE
 +from .worldstarhiphop import WorldStarHipHopIE
 +from .xnxx import XNXXIE
 +from .xhamster import XHamsterIE
 +from .xvideos import XVideosIE
 +from .yahoo import YahooIE, YahooSearchIE
 +from .youjizz import YouJizzIE
 +from .youku import YoukuIE
 +from .youporn import YouPornIE
 +from .youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
 +from .zdf import ZDFIE
 +
 +def gen_extractors():
 +    """ Return a list of an instance of every supported extractor.
 +    The order does matter; the first extractor matched is the one handling the URL.
 +    """
 +    return [
 +        YoutubePlaylistIE(),
 +        YoutubeChannelIE(),
 +        YoutubeUserIE(),
 +        YoutubeSearchIE(),
 +        YoutubeIE(),
 +        MetacafeIE(),
 +        DailymotionIE(),
 +        GoogleSearchIE(),
 +        PhotobucketIE(),
 +        YahooIE(),
 +        YahooSearchIE(),
 +        DepositFilesIE(),
 +        FacebookIE(),
 +        BlipTVIE(),
 +        BlipTVUserIE(),
 +        VimeoIE(),
 +        MyVideoIE(),
 +        ComedyCentralIE(),
 +        EscapistIE(),
 +        CollegeHumorIE(),
 +        XVideosIE(),
 +        SoundcloudSetIE(),
 +        SoundcloudIE(),
 +        InfoQIE(),
 +        MixcloudIE(),
 +        StanfordOpenClassroomIE(),
 +        MTVIE(),
 +        YoukuIE(),
 +        XNXXIE(),
 +        YouJizzIE(),
 +        PornotubeIE(),
 +        YouPornIE(),
 +        GooglePlusIE(),
 +        ArteTvIE(),
 +        NBAIE(),
 +        WorldStarHipHopIE(),
 +        JustinTVIE(),
 +        FunnyOrDieIE(),
 +        SteamIE(),
 +        UstreamIE(),
 +        RBMARadioIE(),
 +        EightTracksIE(),
 +        KeekIE(),
 +        TEDIE(),
 +        MySpassIE(),
 +        SpiegelIE(),
 +        LiveLeakIE(),
 +        ARDIE(),
 +        ZDFIE(),
 +        TumblrIE(),
 +        BandcampIE(),
 +        RedTubeIE(),
 +        InaIE(),
 +        HowcastIE(),
 +        VineIE(),
 +        FlickrIE(),
 +        TeamcocoIE(),
 +        XHamsterIE(),
 +        HypemIE(),
 +        Vbox7IE(),
 +        GametrailersIE(),
 +        StatigramIE(),
++        BreakIE(),
 +        GenericIE()
 +    ]
 +
 +def get_info_extractor(ie_name):
 +    """Returns the info extractor class with the given ie_name"""
 +    return globals()[ie_name+'IE']
index 0000000000000000000000000000000000000000,0000000000000000000000000000000000000000..1f6620d9158d25323e9aeb1c5f172eb74a26a806
new file mode 100644 (file)
--- /dev/null
--- /dev/null
@@@ -1,0 -1,0 +1,25 @@@
++import re
++
++from .common import InfoExtractor
++
++
++class BreakIE(InfoExtractor):
++    _VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)'
++
++    def _real_extract(self, url):
++        mobj = re.match(self._VALID_URL, url)
++        video_id = mobj.group(1).split("-")[-1]
++        webpage = self._download_webpage(url, video_id)
++        video_url = re.search(r"videoPath: '(.+?)',",webpage).group(1)
++        key = re.search(r"icon: '(.+?)',",webpage).group(1)
++        final_url = str(video_url)+"?"+str(key)
++        thumbnail_url = re.search(r"thumbnailURL: '(.+?)'",webpage).group(1)
++        title = re.search(r"sVidTitle: '(.+)',",webpage).group(1)
++        ext = video_url.split('.')[-1]
++        return [{
++            'id':        video_id,
++            'url':       final_url,
++            'ext':       ext,
++            'title':     title,
++            'thumbnail': thumbnail_url,
++        }]