github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

The opening curly brace, '{', is a regex reserved control character, so it needs to be escaped (see http://stackoverflow.com/a/400316/1106367)

Browse source 
Minor improvements:
no need to sort the whole list if all we need is the maximum element, also instead of reinventing the wheel we can use utils to get indices from qualities.
This commit is contained in:
codesparkle 2014-05-19 22:17:54 +10:00
parent 89bb8e97ee
commit 77541837e5
1 changed files with 8 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
youtube_dl/extractor/ndr.py
View file

@ -7,6 +7,7 @@
from ..utils import (
ExtractorError,
int_or_none,
qualities,
)
@ -57,7 +58,7 @@ def _real_extract(self, url):
formats = []
mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
mp3_url = re.search(r'''\{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
if mp3_url:
formats.append({
'url': mp3_url.group('audio'),
@ -66,15 +67,15 @@ def _real_extract(self, url):
thumbnail = None
video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
if video_url:
thumbnails = re.findall(r'''\d+: {src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
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]
quality_key = qualities(['xs', 's', 'm', 'l', 'xl'])
largest = max(thumbnails, key=lambda thumb: quality_key(thumb[1]))
thumbnail = 'http://www.ndr.de' + largest[0]
for format_id in ['lo', 'hi', 'hq']:
for format_id in 'lo', 'hi', 'hq':
formats.append({
'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
'format_id': format_id,