R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

flake8 compliant, allow non-essential uploader field to be None, fallback to video_id as title (current behavior with generic exractor), make filesize int_or_none

Browse Source
This commit is contained in:
iamevn 2017-05-06 02:17:17 -04:00
parent be9e638683
commit feff838741
1 changed files with 12 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
youtube_dl/extractor/full30.py
View File

@ -2,6 +2,7 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import int_or_none
class Full30IE(InfoExtractor):
@ -12,7 +13,7 @@ class Full30IE(InfoExtractor):
'info_dict': {
'id': 'b2a28b99494164ddd55e91a6c4648cbc',
'title': 'Flamethrower Q&A with Charlie Hobson',
'uploader' : 'Forgotten Weapons',
'uploader': 'Forgotten Weapons',
'thumbnail': r're:^https?://.*52130\.jpg$',
'ext': 'ogv',
}
@ -22,7 +23,7 @@ class Full30IE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1 [^>]*class=.video-title[^>]*>([^<]+?)</h1>', webpage, 'title', fatal=False, default=None) or self._og_search_title(webpage)
title = self._html_search_regex(r'<h1 [^>]*class=.video-title[^>]*>([^<]+?)</h1>', webpage, 'title', fatal=False, default=None) or self._og_search_title(webpage) or video_id
uploader = self._html_search_regex(r'<h1 class=.channel-title[^>]*>([^<]+)<', webpage, 'uploader', fatal=False, default=None) or None
thumbnail = self._html_search_regex(r'<[^>]*property=.og:image. ?content="([^>]*thumbnails[^">]*)"\/>', webpage, 'thumbnail', fatal=False, default=None) or self._og_search_thumbnail(webpage)
@ -38,17 +39,14 @@ class Full30IE(InfoExtractor):
# turn sequence of json entries into an actual list
vid_json = vid_json.rstrip()
vid_json = "[" + vid_json + "]"
vid_json = vid_json.replace("}", "},").replace(",]","]")
vid_json = vid_json.replace("}", "},").replace(",]", "]")
parsed = self._parse_json(vid_json, video_id)
formats = []
for d in parsed:
if d["type"] == "object":
formats.append({
"url" : vid_path + d["name"],
"resolution" : d["name"][:d["name"].rfind(".")],
"filesize" : d["size"],
})
formats = [{
"url": vid_path + entry["name"],
"resolution": entry["name"][:entry["name"].rfind(".")],
"filesize": int_or_none(entry["size"]),
} for entry in parsed if entry.get("type") == "object"]
self._sort_formats(formats)
@ -56,6 +54,6 @@ class Full30IE(InfoExtractor):
'id': video_id,
'title': title,
'uploader': uploader,
'thumbnail' : thumbnail,
'formats' : formats,
'thumbnail': thumbnail,
'formats': formats,
}