diff options
author | Sergey M․ <[email protected]> | 2014-12-21 07:33:58 +0600 |
---|---|---|
committer | Sergey M․ <[email protected]> | 2014-12-21 07:33:58 +0600 |
commit | 081d6e47840fb923ed6f565fa56dd5def9b9a184 (patch) | |
tree | cc9bf92e95f3383366ed87cedc8aa8c9359fa9a2 /youtube_dl/extractor/dvtv.py | |
parent | 1d4247f64e4124476f807e9eeb58fd401ffcd8ae (diff) | |
download | youtube-dl-081d6e47840fb923ed6f565fa56dd5def9b9a184.tar.gz youtube-dl-081d6e47840fb923ed6f565fa56dd5def9b9a184.zip |
[dvtv] Simplify
Diffstat (limited to 'youtube_dl/extractor/dvtv.py')
-rw-r--r-- | youtube_dl/extractor/dvtv.py | 36 |
1 files changed, 19 insertions, 17 deletions
diff --git a/youtube_dl/extractor/dvtv.py b/youtube_dl/extractor/dvtv.py index 2449b03b5..5f8ac3e46 100644 --- a/youtube_dl/extractor/dvtv.py +++ b/youtube_dl/extractor/dvtv.py @@ -1,5 +1,4 @@ # coding: utf-8 - from __future__ import unicode_literals import re @@ -8,7 +7,7 @@ from .common import InfoExtractor from ..utils import ( js_to_json, unescapeHTML, - ExtractorError + ExtractorError, ) @@ -16,7 +15,7 @@ class DVTVIE(InfoExtractor): IE_NAME = 'dvtv' IE_DESC = 'http://video.aktualne.cz/' - _VALID_URL = r'http://video\.aktualne\.cz/.*/r~(?P<id>[0-9a-f]{32})/' + _VALID_URL = r'http://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})' _TESTS = [{ 'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/', @@ -24,7 +23,7 @@ class DVTVIE(InfoExtractor): 'info_dict': { 'id': 'dc0768de855511e49e4b0025900fea04', 'ext': 'mp4', - 'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně' + 'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně', } }, { 'url': 'http://video.aktualne.cz/dvtv/stropnicky-policie-vrbetice-preventivne-nekontrolovala/r~82ed4322849211e4a10c0025900fea04/', @@ -32,13 +31,13 @@ class DVTVIE(InfoExtractor): 'info_dict': { 'id': '72c02230849211e49f60002590604f2e', 'ext': 'mp4', - 'title': 'Stropnický: Policie Vrbětice preventivně nekontrolovala' + 'title': 'Stropnický: Policie Vrbětice preventivně nekontrolovala', } }, { 'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/', 'info_dict': { 'title': 'DVTV 16. 12. 2014: útok Talibanu, boj o kliniku, uprchlíci', - 'id': '973eb3bc854e11e498be002590604f2e' + 'id': '973eb3bc854e11e498be002590604f2e', }, 'playlist': [{ 'md5': 'da7ca6be4935532241fa9520b3ad91e4', @@ -68,7 +67,10 @@ class DVTVIE(InfoExtractor): 'ext': 'mp4', 'title': 'Pánek: Odmítání syrských uprchlíků je ostudou české vlády' } - }] + }], + }, { + 'url': 'http://video.aktualne.cz/v-cechach-poprve-zazni-zelenkova-zrestaurovana-mse/r~45b4b00483ec11e4883b002590604f2e/', + 'only_matching': True, }] def _parse_video_metadata(self, js, video_id): @@ -80,7 +82,6 @@ class DVTVIE(InfoExtractor): formats.append({ 'url': video['file'], 'ext': ext, - 'format': '%s %s' % (ext, video['label']), 'format_id': '%s-%s' % (ext, video['label']), 'height': int(video['label'].rstrip('p')), 'fps': 25, @@ -91,25 +92,26 @@ class DVTVIE(InfoExtractor): return { 'id': metadata['mediaid'], 'title': unescapeHTML(metadata['title']), - 'thumbnail': 'http:%s' % metadata['image'], + 'thumbnail': self._proto_relative_url(metadata['image']), 'formats': formats } def _real_extract(self, url): video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - # singe video - items = re.findall( - r'(?s)embedData[0-9a-f]{32}\[\'asset\'\] = (\{.+?\});', - webpage) + # single video + item = self._search_regex( + r"(?s)embedData[0-9a-f]{32}\['asset'\]\s*=\s*(\{.+?\});", + webpage, 'video', default=None, fatal=False) - if items: - return self._parse_video_metadata(items[0], video_id) + if item: + return self._parse_video_metadata(item, video_id) # playlist items = re.findall( - r'(?s)BBX\.context\.assets\[\'[0-9a-f]{32}\'\]\.push\((\{.+?\})\);', + r"(?s)BBX\.context\.assets\['[0-9a-f]{32}'\]\.push\(({.+?})\);", webpage) if items: @@ -120,4 +122,4 @@ class DVTVIE(InfoExtractor): 'entries': [self._parse_video_metadata(i, video_id) for i in items] } - raise ExtractorError('Could not find neither video nor playlist for requested ID') + raise ExtractorError('Could not find neither video nor playlist') |