github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[newgrounds] improve metadata extraction

Browse Source
This commit is contained in:
Mike Fährmann
2019-07-08 17:53:16 +02:00
parent 12da6bd0c9
commit 04b8d0894a
1 changed files with 6 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
gallery_dl/extractor/newgrounds.py
View File

@@ -48,22 +48,20 @@ class NewgroundsExtractor(Extractor):
extr = text.extract_from(self.request(page_url).text) extr = text.extract_from(self.request(page_url).text)
full = text.extract_from(json.loads(extr('"full_image_text":', '});'))) full = text.extract_from(json.loads(extr('"full_image_text":', '});')))
data = { data = {
"title" : text.unescape(extr('"og:title" content="', '"')),
"description": text.unescape(extr(':description" content="', '"')), "description": text.unescape(extr(':description" content="', '"')),
"date" : extr('itemprop="datePublished" content="', '"'), "date" : text.parse_datetime(extr(
'itemprop="datePublished" content="', '"')),
"rating" : extr('class="rated-', '"'), "rating" : extr('class="rated-', '"'),
"favorites" : text.parse_int(extr('id="faves_load">', '<')), "favorites" : text.parse_int(extr('id="faves_load">', '<')),
"score" : text.parse_float(extr('id="score_number">', '<')), "score" : text.parse_float(extr('id="score_number">', '<')),
"tags" : text.split_html(extr(
'<dd class="tags momag">', '</dd>')),
"url" : full('src="', '"'), "url" : full('src="', '"'),
"title" : text.unescape(full('alt="', '"')),
"width" : text.parse_int(full('width="', '"')), "width" : text.parse_int(full('width="', '"')),
"height" : text.parse_int(full('height="', '"')), "height" : text.parse_int(full('height="', '"')),
} }
data["tags"].sort()
tags = text.split_html(extr('<dd class="tags momag">', '</dd>'))
tags.sort()
data["tags"] = tags
data["date"] = text.parse_datetime(data["date"])
data["index"] = text.parse_int( data["index"] = text.parse_int(
data["url"].rpartition("/")[2].partition("_")[0]) data["url"].rpartition("/")[2].partition("_")[0])
return data return data