diff options
Diffstat (limited to 'youtube_dl')
| -rw-r--r-- | youtube_dl/extractor/generic.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/netzkino.py | 3 | ||||
| -rw-r--r-- | youtube_dl/extractor/sockshare.py | 5 | ||||
| -rw-r--r-- | youtube_dl/extractor/theonion.py | 17 | ||||
| -rw-r--r-- | youtube_dl/extractor/webofstories.py | 22 |
5 files changed, 21 insertions, 28 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 36a1f65bf..8dce96a64 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -532,7 +532,7 @@ class GenericIE(InfoExtractor): 'info_dict': { 'id': 'Mrj4DVp2zeA', 'ext': 'mp4', - 'upload_date': '20150204', + 'upload_date': '20150212', 'uploader': 'The National Archives UK', 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6', 'uploader_id': 'NationalArchives08', diff --git a/youtube_dl/extractor/netzkino.py b/youtube_dl/extractor/netzkino.py index 93567d1e3..bc17e20aa 100644 --- a/youtube_dl/extractor/netzkino.py +++ b/youtube_dl/extractor/netzkino.py @@ -29,6 +29,9 @@ class NetzkinoIE(InfoExtractor): 'timestamp': 1344858571, 'age_limit': 12, }, + 'params': { + 'skip_download': 'Download only works from Germany', + } } def _real_extract(self, url): diff --git a/youtube_dl/extractor/sockshare.py b/youtube_dl/extractor/sockshare.py index 7d3c0e937..b5fa6f1da 100644 --- a/youtube_dl/extractor/sockshare.py +++ b/youtube_dl/extractor/sockshare.py @@ -25,7 +25,6 @@ class SockshareIE(InfoExtractor): 'id': '437BE28B89D799D7', 'title': 'big_buck_bunny_720p_surround.avi', 'ext': 'avi', - 'thumbnail': 're:^http://.*\.jpg$', } } @@ -45,7 +44,7 @@ class SockshareIE(InfoExtractor): ''', webpage, 'hash') fields = { - "hash": confirm_hash, + "hash": confirm_hash.encode('utf-8'), "confirm": "Continue as Free User" } @@ -68,7 +67,7 @@ class SockshareIE(InfoExtractor): webpage, 'title', default=None) thumbnail = self._html_search_regex( r'<img\s+src="([^"]*)".+?name="bg"', - webpage, 'thumbnail') + webpage, 'thumbnail', default=None) formats = [{ 'format_id': 'sd', diff --git a/youtube_dl/extractor/theonion.py b/youtube_dl/extractor/theonion.py index b65d8e03f..10239c906 100644 --- a/youtube_dl/extractor/theonion.py +++ b/youtube_dl/extractor/theonion.py @@ -4,11 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ExtractorError class TheOnionIE(InfoExtractor): - _VALID_URL = r'(?x)https?://(?:www\.)?theonion\.com/video/[^,]+,(?P<article_id>[0-9]+)/?' + _VALID_URL = r'https?://(?:www\.)?theonion\.com/video/[^,]+,(?P<id>[0-9]+)/?' _TEST = { 'url': 'http://www.theonion.com/video/man-wearing-mm-jacket-gods-image,36918/', 'md5': '19eaa9a39cf9b9804d982e654dc791ee', @@ -22,10 +21,8 @@ class TheOnionIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - article_id = mobj.group('article_id') - - webpage = self._download_webpage(url, article_id) + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) video_id = self._search_regex( r'"videoId":\s(\d+),', webpage, 'video ID') @@ -34,10 +31,6 @@ class TheOnionIE(InfoExtractor): thumbnail = self._og_search_thumbnail(webpage) sources = re.findall(r'<source src="([^"]+)" type="([^"]+)"', webpage) - if not sources: - raise ExtractorError( - 'No sources found for video %s' % video_id, expected=True) - formats = [] for src, type_ in sources: if type_ == 'video/mp4': @@ -54,15 +47,15 @@ class TheOnionIE(InfoExtractor): }) elif type_ == 'application/x-mpegURL': formats.extend( - self._extract_m3u8_formats(src, video_id, preference=-1)) + self._extract_m3u8_formats(src, display_id, preference=-1)) else: self.report_warning( 'Encountered unexpected format: %s' % type_) - self._sort_formats(formats) return { 'id': video_id, + 'display_id': display_id, 'title': title, 'formats': formats, 'thumbnail': thumbnail, diff --git a/youtube_dl/extractor/webofstories.py b/youtube_dl/extractor/webofstories.py index 396cf4e83..73077a312 100644 --- a/youtube_dl/extractor/webofstories.py +++ b/youtube_dl/extractor/webofstories.py @@ -45,19 +45,17 @@ class WebOfStoriesIE(InfoExtractor): description = self._html_search_meta('description', webpage) thumbnail = self._og_search_thumbnail(webpage) - story_filename = self._search_regex( - r'\.storyFileName\("([^"]+)"\)', webpage, 'story filename') - speaker_id = self._search_regex( - r'\.speakerId\("([^"]+)"\)', webpage, 'speaker ID') - story_id = self._search_regex( - r'\.storyId\((\d+)\)', webpage, 'story ID') - speaker_type = self._search_regex( - r'\.speakerType\("([^"]+)"\)', webpage, 'speaker type') - great_life = self._search_regex( - r'isGreatLifeStory\s*=\s*(true|false)', webpage, 'great life story') + embed_params = [s.strip(" \r\n\t'") for s in self._search_regex( + r'(?s)\$\("#embedCode"\).html\(getEmbedCode\((.*?)\)', + webpage, 'embed params').split(',')] + + ( + _, speaker_id, story_id, story_duration, + speaker_type, great_life, _thumbnail, _has_subtitles, + story_filename, _story_order) = embed_params + is_great_life_series = great_life == 'true' - duration = int_or_none(self._search_regex( - r'\.duration\((\d+)\)', webpage, 'duration', fatal=False)) + duration = int_or_none(story_duration) # URL building, see: http://www.webofstories.com/scripts/player.js ms_prefix = '' |