diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/common.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/screencast.py | 69 |
2 files changed, 60 insertions, 13 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index f1ed30704..e68657314 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -463,14 +463,14 @@ class InfoExtractor(object): def _og_search_url(self, html, **kargs): return self._og_search_property('url', html, **kargs) - def _html_search_meta(self, name, html, display_name=None, fatal=False): + def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs): if display_name is None: display_name = name return self._html_search_regex( r'''(?ix)<meta (?=[^>]+(?:itemprop|name|property)=["\']%s["\']) [^>]+content=["\']([^"\']+)["\']''' % re.escape(name), - html, display_name, fatal=fatal) + html, display_name, fatal=fatal, **kwargs) def _dc_search_uploader(self, html): return self._html_search_meta('dc.creator', html, 'uploader') diff --git a/youtube_dl/extractor/screencast.py b/youtube_dl/extractor/screencast.py index f2ced39c4..ba69739b2 100644 --- a/youtube_dl/extractor/screencast.py +++ b/youtube_dl/extractor/screencast.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( + ExtractorError, compat_parse_qs, compat_urllib_request, ) @@ -12,7 +13,7 @@ from ..utils import ( class ScreencastIE(InfoExtractor): _VALID_URL = r'https?://www\.screencast\.com/t/(?P<id>[a-zA-Z0-9]+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.screencast.com/t/3ZEjQXlT', 'md5': '917df1c13798a3e96211dd1561fded83', 'info_dict': { @@ -20,24 +21,70 @@ class ScreencastIE(InfoExtractor): 'ext': 'm4v', 'title': 'Color Measurement with Ocean Optics Spectrometers', 'description': 'md5:240369cde69d8bed61349a199c5fb153', - 'thumbnail': 're:^https?://.*\.jpg$' + 'thumbnail': 're:^https?://.*\.(?:gif|jpg)$', } - } + }, { + 'url': 'http://www.screencast.com/t/V2uXehPJa1ZI', + 'md5': 'e8e4b375a7660a9e7e35c33973410d34', + 'info_dict': { + 'id': 'V2uXehPJa1ZI', + 'ext': 'mov', + 'title': 'The Amadeus Spectrometer', + 'description': 're:^In this video, our friends at.*To learn more about Amadeus, visit', + 'thumbnail': 're:^https?://.*\.(?:gif|jpg)$', + } + }, { + 'url': 'http://www.screencast.com/t/aAB3iowa', + 'md5': 'dedb2734ed00c9755761ccaee88527cd', + 'info_dict': { + 'id': 'aAB3iowa', + 'ext': 'mp4', + 'title': 'Google Earth Export', + 'description': 'Provides a demo of a CommunityViz export to Google Earth, one of the 3D viewing options.', + 'thumbnail': 're:^https?://.*\.(?:gif|jpg)$', + } + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - flash_vars_s = self._html_search_regex( - r'<param name="flashVars" value="([^"]+)"', webpage, 'flash vars') - flash_vars = compat_parse_qs(flash_vars_s) + video_url = self._html_search_regex( + r'<embed name="Video".*?src="([^"]+)"', webpage, + 'QuickTime embed', default=None) + + if video_url is None: + flash_vars_s = self._html_search_regex( + r'<param name="flashVars" value="([^"]+)"', webpage, 'flash vars', + default=None) + if flash_vars_s: + flash_vars = compat_parse_qs(flash_vars_s) + video_url_raw = compat_urllib_request.quote( + flash_vars['content'][0]) + video_url = video_url_raw.replace('http%3A', 'http:') + + if video_url is None: + video_meta = self._html_search_meta( + 'og:video', webpage, default=None) + if video_meta: + video_url = self._search_regex( + r'src=(.*?)(?:$|&)', video_meta, + 'meta tag video URL', default=None) + + if video_url is None: + raise ExtractorError('Cannot find video') - thumbnail = flash_vars.get('thumb', [None])[0] - video_url_raw = compat_urllib_request.quote(flash_vars['content'][0]) - video_url = video_url_raw.replace('http%3A', 'http:') - title = self._og_search_title(webpage) - description = self._og_search_description(webpage) + title = self._og_search_title(webpage, default=None) + if title is None: + title = self._html_search_regex( + r'class="tabSeperator">></span><span class="tabText">(.*?)<', + webpage, 'title') + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage, default=None) + if description is None: + description = self._html_search_meta('description', webpage) return { 'id': video_id, |