X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsenateisvp.py;h=d3b8a1be49702f71a1a8c4eb7bd01d17cf103071;hb=0b9f7cd074786abafcd35b26db4ecb4d92814393;hp=a93874cad9f83ffa36214f1bac5ae6863072ae95;hpb=f91e1a8739a59bca1ced0bbc70f8cf9c3a33f778;p=youtube-dl diff --git a/youtube_dl/extractor/senateisvp.py b/youtube_dl/extractor/senateisvp.py index a93874cad..d3b8a1be4 100644 --- a/youtube_dl/extractor/senateisvp.py +++ b/youtube_dl/extractor/senateisvp.py @@ -3,7 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + unsmuggle_url, +) from ..compat import ( compat_parse_qs, compat_urlparse, @@ -48,7 +51,6 @@ class SenateISVPIE(InfoExtractor): _VALID_URL = r'http://www\.senate\.gov/isvp/\?(?P.+)' _TESTS = [{ 'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png', - 'md5': '7314c4b96dad66dd8e63dc3518ceaa6f', 'info_dict': { 'id': 'judiciary031715', 'ext': 'flv', @@ -57,7 +59,6 @@ class SenateISVPIE(InfoExtractor): } }, { 'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false', - 'md5': '2917c827513700aa9b70eaebf25116da', 'info_dict': { 'id': 'commerce011514', 'ext': 'flv', @@ -73,12 +74,22 @@ class SenateISVPIE(InfoExtractor): } }] + @staticmethod + def _search_iframe_url(webpage): + mobj = re.search( + r"]+src=['\"](?Phttp://www\.senate\.gov/isvp/\?[^'\"]+)['\"]", + webpage) + if mobj: + return mobj.group('url') + def _get_info_for_comm(self, committee): for entry in self._COMM_MAP: if entry[0] == committee: return entry[1:] def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) + qs = compat_parse_qs(re.match(self._VALID_URL, url).group('qs')) if not qs.get('filename') or not qs.get('type') or not qs.get('comm'): raise ExtractorError('Invalid URL', expected=True) @@ -87,10 +98,12 @@ class SenateISVPIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'([^<]+)', webpage, video_id) + if smuggled_data.get('force_title'): + title = smuggled_data['force_title'] + else: + title = self._html_search_regex(r'([^<]+)', webpage, video_id) poster = qs.get('poster') - if poster: - thumbnail = poster[0] + thumbnail = poster[0] if poster else None video_type = qs['type'][0] committee = video_type if video_type == 'arch' else qs['comm'][0] @@ -120,15 +133,9 @@ class SenateISVPIE(InfoExtractor): self._sort_formats(formats) - info_dict = { + return { 'id': video_id, 'title': title, + 'formats': formats, 'thumbnail': thumbnail, } - - if len(formats) >= 1: - info_dict.update({'formats': formats}) - else: - info_dict.update(formats[0]) - - return info_dict