diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/generic.py | 11 | ||||
| -rw-r--r-- | youtube_dl/extractor/ndr.py | 24 | ||||
| -rw-r--r-- | youtube_dl/extractor/nowness.py | 9 |
3 files changed, 26 insertions, 18 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 286133282..38a357d3b 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -363,8 +363,13 @@ class GenericIE(InfoExtractor): return self.url_result('http://' + url) else: if default_search == 'auto_warning': - self._downloader.report_warning( - 'Falling back to youtube search for %s . Set --default-search to "auto" to suppress this warning.' % url) + if re.match(r'^(?:url|URL)$', url): + raise ExtractorError( + 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url, + expected=True) + else: + self._downloader.report_warning( + 'Falling back to youtube search for %s . Set --default-search to "auto" to suppress this warning.' % url) return self.url_result('ytsearch:' + url) else: assert ':' in default_search @@ -560,7 +565,7 @@ class GenericIE(InfoExtractor): # Look for embedded NovaMov-based player mobj = re.search( - r'''(?x)<iframe[^>]+?src=(["\']) + r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\']) (?P<url>http://(?:(?:embed|www)\.)? (?:novamov\.com| nowvideo\.(?:ch|sx|eu|at|ag|co)| diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index 0650f9564..53b34f5e6 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -4,7 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + int_or_none, +) class NDRIE(InfoExtractor): @@ -45,13 +48,12 @@ class NDRIE(InfoExtractor): page = self._download_webpage(url, video_id, 'Downloading page') - title = self._og_search_title(page) + title = self._og_search_title(page).strip() description = self._og_search_description(page) + if description: + description = description.strip() - mobj = re.search( - r'<div class="duration"><span class="min">(?P<minutes>\d+)</span>:<span class="sec">(?P<seconds>\d+)</span></div>', - page) - duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None + duration = int_or_none(self._html_search_regex(r'duration: (\d+),\n', page, 'duration', fatal=False)) formats = [] @@ -66,10 +68,12 @@ class NDRIE(InfoExtractor): video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page) if video_url: - thumbnail = self._html_search_regex(r'(?m)title: "NDR PLAYER",\s*poster: "([^"]+)",', - page, 'thumbnail', fatal=False) - if thumbnail: - thumbnail = 'http://www.ndr.de' + thumbnail + thumbnails = re.findall(r'''\d+: {src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page) + if thumbnails: + QUALITIES = ['xs', 's', 'm', 'l', 'xl'] + thumbnails.sort(key=lambda thumb: QUALITIES.index(thumb[1]) if thumb[1] in QUALITIES else -1) + thumbnail = 'http://www.ndr.de' + thumbnails[-1][0] + for format_id in ['lo', 'hi', 'hq']: formats.append({ 'url': '%s.%s.mp4' % (video_url.group('video'), format_id), diff --git a/youtube_dl/extractor/nowness.py b/youtube_dl/extractor/nowness.py index b1bcb7e54..1c5e9401f 100644 --- a/youtube_dl/extractor/nowness.py +++ b/youtube_dl/extractor/nowness.py @@ -4,9 +4,7 @@ import re from .brightcove import BrightcoveIE from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) +from ..utils import ExtractorError class NownessIE(InfoExtractor): @@ -14,9 +12,10 @@ class NownessIE(InfoExtractor): _TEST = { 'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation', - 'file': '2520295746001.mp4', - 'md5': '0ece2f70a7bd252c7b00f3070182d418', + 'md5': '068bc0202558c2e391924cb8cc470676', 'info_dict': { + 'id': '2520295746001', + 'ext': 'mp4', 'description': 'Candor: The Art of Gesticulation', 'uploader': 'Nowness', 'title': 'Candor: The Art of Gesticulation', |