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

cleaned up, added fallbacks

Browse Source
This commit is contained in:
iamevn 2017-05-05 00:42:22 -04:00
parent 957a681148
commit be9e638683
1 changed files with 21 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
youtube_dl/extractor/full30.py
View File

@ -11,15 +11,10 @@ class Full30IE(InfoExtractor):
'md5': 'f5aa3862cbe35c2083ce050ac1a5eb06', 'md5': 'f5aa3862cbe35c2083ce050ac1a5eb06',
'info_dict': { 'info_dict': {
'id': 'b2a28b99494164ddd55e91a6c4648cbc', 'id': 'b2a28b99494164ddd55e91a6c4648cbc',
'ext': 'ogv',
'title': 'Flamethrower Q&A with Charlie Hobson', 'title': 'Flamethrower Q&A with Charlie Hobson',
'thumbnail': r're:^https?://.*52130\.jpg$',
'uploader' : 'Forgotten Weapons', 'uploader' : 'Forgotten Weapons',
# TODO more properties, either as: 'thumbnail': r're:^https?://.*52130\.jpg$',
# * A value 'ext': 'ogv',
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
} }
} }
@ -27,28 +22,32 @@ 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)
# TODO more code goes here, for example ... 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') 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) thumbnail = self._html_search_regex(r'<[^>]*property=.og:image. ?content="([^>]*thumbnails[^">]*)"\/>', webpage, 'thumbnail', fatal=False, default=None) or self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage)
thumbnail = self._html_search_regex(r'<[^>]*property=.og:image. ?content="([^>]*thumbnails[^">]*)"\/>', webpage, 'thumbnail', fatal=False) or self._og_search_thumbnail(webpage)
vidpath = self._html_search_regex(r'<input id=.video-path[^>]*value=["\']([^"\']*)["\'][^>]*>', webpage, 'video_path', fatal=False) # looking for a line like the following
vidjson = self._download_webpage(vidpath, video_id) # <input id="video-path" type="hidden" name="video_path" value="https://videos.full30.com/bitmotive/public/full30/v1.0/videos/forgottenweapons/b2a28b99494164ddd55e91a6c4648cbc/" />
# this is robust # there's also a full30.com/cdn which appears to have the same sort of structure. it's possible that either of these may go away so as a backup I'll build the cdn link out from channel slug
vidjson = vidjson.rstrip() vid_path = self._html_search_regex(r'<input id=.video-path[^>]*value=["\']([^"\']*)["\'][^>]*>', webpage, 'video_path', fatal=False, default=None)
vidjson = "[" + vidjson + "]" if not vid_path:
vidjson = vidjson.replace("}", "},").replace(",]","]") channel_slug = self._html_search_regex(r'<input id=.channel-slug[^>]*value=["\']([^"\']*)["\'][^>]*>', webpage, 'channel_slug', fatal=True)
parsed = self._parse_json(vidjson, video_id) vid_path = "https://www.full30.com/cdn/videos/" + channel_slug + "/" + video_id + "/"
vid_json = self._download_webpage(vid_path, video_id)
# turn sequence of json entries into an actual list
vid_json = vid_json.rstrip()
vid_json = "[" + vid_json + "]"
vid_json = vid_json.replace("}", "},").replace(",]","]")
parsed = self._parse_json(vid_json, video_id)
formats = [] formats = []
for d in parsed: for d in parsed:
if d["type"] == "object": if d["type"] == "object":
formats.append({ formats.append({
"url" : vidpath + d["name"], "url" : vid_path + d["name"],
"resolution" : d["name"][:d["name"].rfind(".")], "resolution" : d["name"][:d["name"].rfind(".")],
"filesize" : d["size"], "filesize" : d["size"],
"protocol" : "https"
}) })
self._sort_formats(formats) self._sort_formats(formats)
@ -56,11 +55,7 @@ class Full30IE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
# 'description': description,
'uploader': uploader, 'uploader': uploader,
# 'url' : url,
'formats' : formats,
# TODO more properties (see youtube_dl/extractor/common.py)
'ext': 'mp4',
'thumbnail' : thumbnail, 'thumbnail' : thumbnail,
'formats' : formats,
} }