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

26
youtube_dl/extractor/full30.py
View File

@ -2,6 +2,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import int_or_none
class Full30IE(InfoExtractor): class Full30IE(InfoExtractor):
@ -12,7 +13,7 @@ class Full30IE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': 'b2a28b99494164ddd55e91a6c4648cbc', 'id': 'b2a28b99494164ddd55e91a6c4648cbc',
'title': 'Flamethrower Q&A with Charlie Hobson', 'title': 'Flamethrower Q&A with Charlie Hobson',
'uploader' : 'Forgotten Weapons', 'uploader': 'Forgotten Weapons',
'thumbnail': r're:^https?://.*52130\.jpg$', 'thumbnail': r're:^https?://.*52130\.jpg$',
'ext': 'ogv', 'ext': 'ogv',
} }
@ -22,8 +23,8 @@ class Full30IE(InfoExtractor):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) 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 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) thumbnail = self._html_search_regex(r'<[^>]*property=.og:image. ?content="([^>]*thumbnails[^">]*)"\/>', webpage, 'thumbnail', fatal=False, default=None) or self._og_search_thumbnail(webpage)
# looking for a line like the following # looking for a line like the following
@ -38,17 +39,14 @@ class Full30IE(InfoExtractor):
# turn sequence of json entries into an actual list # turn sequence of json entries into an actual list
vid_json = vid_json.rstrip() vid_json = vid_json.rstrip()
vid_json = "[" + vid_json + "]" vid_json = "[" + vid_json + "]"
vid_json = vid_json.replace("}", "},").replace(",]","]") vid_json = vid_json.replace("}", "},").replace(",]", "]")
parsed = self._parse_json(vid_json, video_id) parsed = self._parse_json(vid_json, video_id)
formats = [] formats = [{
for d in parsed: "url": vid_path + entry["name"],
if d["type"] == "object": "resolution": entry["name"][:entry["name"].rfind(".")],
formats.append({ "filesize": int_or_none(entry["size"]),
"url" : vid_path + d["name"], } for entry in parsed if entry.get("type") == "object"]
"resolution" : d["name"][:d["name"].rfind(".")],
"filesize" : d["size"],
})
self._sort_formats(formats) self._sort_formats(formats)
@ -56,6 +54,6 @@ class Full30IE(InfoExtractor):
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'uploader': uploader, 'uploader': uploader,
'thumbnail' : thumbnail, 'thumbnail': thumbnail,
'formats' : formats, 'formats': formats,
} }