diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/generic.py | 6 | ||||
| -rw-r--r-- | youtube_dl/extractor/viddler.py | 64 |
3 files changed, 68 insertions, 3 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index d1b7e5f99..2b054e1c9 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -117,6 +117,7 @@ from .veehd import VeeHDIE from .veoh import VeohIE from .vevo import VevoIE from .vice import ViceIE +from .viddler import ViddlerIE from .videofyme import VideofyMeIE from .vimeo import VimeoIE, VimeoChannelIE from .vine import VineIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 764070635..7060c6f92 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -117,7 +117,7 @@ class GenericIE(InfoExtractor): except ValueError: # since this is the last-resort InfoExtractor, if # this error is thrown, it'll be thrown here - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError(u'Failed to download URL: %s' % url) self.report_extraction(video_id) # Look for BrightCove: @@ -149,12 +149,12 @@ class GenericIE(InfoExtractor): # HTML5 video mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError(u'Unsupported 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) + raise ExtractorError(u'Did not find a valid video URL at %s' % url) video_url = mobj.group(1) video_url = compat_urlparse.urljoin(url, video_url) diff --git a/youtube_dl/extractor/viddler.py b/youtube_dl/extractor/viddler.py new file mode 100644 index 000000000..12c84a985 --- /dev/null +++ b/youtube_dl/extractor/viddler.py @@ -0,0 +1,64 @@ +import json +import re + +from .common import InfoExtractor +from ..utils import ( + determine_ext, +) + + +class ViddlerIE(InfoExtractor): + _VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler.com)/(?:v|embed|player)/(?P<id>[0-9]+)' + _TEST = { + u"url": u"http://www.viddler.com/v/43903784", + u'file': u'43903784.mp4', + u'md5': u'fbbaedf7813e514eb7ca30410f439ac9', + u'info_dict': { + u"title": u"Video Made Easy", + u"uploader": u"viddler", + u"duration": 100.89, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + embed_url = mobj.group('domain') + u'/embed/' + video_id + webpage = self._download_webpage(embed_url, video_id) + + video_sources_code = self._search_regex( + r"(?ms)sources\s*:\s*(\{.*?\})", webpage, u'video URLs') + video_sources = json.loads(video_sources_code.replace("'", '"')) + + formats = [{ + 'url': video_url, + 'format': format_id, + } for video_url, format_id in video_sources.items()] + + title = self._html_search_regex( + r"title\s*:\s*'([^']*)'", webpage, u'title') + uploader = self._html_search_regex( + r"authorName\s*:\s*'([^']*)'", webpage, u'uploader', fatal=False) + duration_s = self._html_search_regex( + r"duration\s*:\s*([0-9.]*)", webpage, u'duration', fatal=False) + duration = float(duration_s) if duration_s else None + thumbnail = self._html_search_regex( + r"thumbnail\s*:\s*'([^']*)'", + webpage, u'thumbnail', fatal=False) + + info = { + '_type': 'video', + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'duration': duration, + 'formats': formats, + } + + # TODO: Remove when #980 has been merged + info['formats'][-1]['ext'] = determine_ext(info['formats'][-1]['url']) + info.update(info['formats'][-1]) + + return info |