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

[pururin] fix extraction

Browse Source 
Missing metadata information would lead to unnecessary exceptions.
This commit is contained in:
Mike Fährmann
2019-06-24 22:27:50 +02:00
parent 98554cbab8
commit 082cb24acd
1 changed files with 57 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

111
gallery_dl/extractor/pururin.py
View File

@@ -17,29 +17,34 @@ class PururinGalleryExtractor(GalleryExtractor):
"""Extractor for image galleries on pururin.io""" """Extractor for image galleries on pururin.io"""
category = "pururin" category = "pururin"
pattern = r"(?:https?://)?(?:www\.)?pururin\.io/(?:gallery|read)/(\d+)" pattern = r"(?:https?://)?(?:www\.)?pururin\.io/(?:gallery|read)/(\d+)"
test = ("https://pururin.io/gallery/38661/iowant-2", { test = (
"pattern": r"https://cdn.pururin.io/assets/images/data/38661/\d+\.jpg", ("https://pururin.io/gallery/38661/iowant-2", {
"keyword": { "pattern": r"https://cdn.pururin.io/\w+/images/data/\d+/\d+\.jpg",
"title" : "Iowant 2!!", "keyword": {
"title_en" : "Iowant 2!!", "title" : "Iowant 2!!",
"title_jp" : "", "title_en" : "Iowant 2!!",
"gallery_id": 38661, "title_jp" : "",
"count" : 19, "gallery_id": 38661,
"artist" : ["Shoda Norihiro"], "count" : 19,
"group" : ["Obsidian Order"], "artist" : ["Shoda Norihiro"],
"parody" : ["Kantai Collection"], "group" : ["Obsidian Order"],
"characters": ["Iowa", "Teitoku"], "parody" : ["Kantai Collection"],
"tags" : list, "characters": ["Iowa", "Teitoku"],
"type" : "Doujinshi", "tags" : list,
"collection": "", "type" : "Doujinshi",
"convention": "C92", "collection": "",
"rating" : float, "convention": "C92",
"uploader" : "demo", "rating" : float,
"scanlator" : "", "uploader" : "demo",
"lang" : "en", "scanlator" : "",
"language" : "English", "lang" : "en",
} "language" : "English",
}) }
}),
("https://pururin.io/gallery/7661/unisis-team-vanilla", {
"count": 17,
}),
)
root = "https://pururin.io" root = "https://pururin.io"
def __init__(self, match): def __init__(self, match):
@@ -51,45 +56,43 @@ class PururinGalleryExtractor(GalleryExtractor):
self._cnt = 0 self._cnt = 0
def metadata(self, page): def metadata(self, page):
data = text.extract_all(page, ( extr = text.extract_from(page)
("artist" , "<td>Artist</td>" , "</td>"),
("group" , "<td>Circle</td>" , "</td>"), def _lst(key, e=extr):
("parody" , "<td>Parody</td>" , "</td>"), return [
("tags" , "<td>Contents</td>" , "</td>"), text.unescape(item)
("type" , "<td>Category</td>" , "</td>"), for item in text.extract_iter(e(key, "</td>"), 'title="', '"')
("characters", "<td>Character</td>" , "</td>"), ]
("collection", "<td>Collection</td>", "</td>"),
("language" , "<td>Language</td>" , "</td>"), def _str(key, e=extr):
("scanlator" , "<td>Scanlator</td>" , "</td>"), return text.unescape(text.extract(
("convention", "<td>Convention</td>", "</td>"), e(key, "</td>"), 'title="', '"')[0] or "")
("uploader" , "<td>Uploader</td>" , "</td>"),
("rating" , " :rating='" , "'"),
))[0]
url = "{}/read/{}/01/x".format(self.root, self.gallery_id) url = "{}/read/{}/01/x".format(self.root, self.gallery_id)
page = self.request(url).text page = self.request(url).text
info = json.loads(text.unescape(text.extract( info = json.loads(text.unescape(text.extract(
page, ':gallery="', '"')[0])) page, ':gallery="', '"')[0]))
self._ext = info["image_extension"] self._ext = info["image_extension"]
self._cnt = info["total_pages"] self._cnt = info["total_pages"]
for key in ("artist", "group", "parody", "tags", "characters"): data = {
data[key] = [ "gallery_id": text.parse_int(self.gallery_id),
text.unescape(item) "title" : info["title"] or info.get("j_title") or "",
for item in text.extract_iter(data[key], 'title="', '"') "title_en" : info["title"],
] "title_jp" : info.get("j_title") or "",
for key in ("type", "collection", "language", "scanlator", "artist" : _lst("<td>Artist</td>"),
"convention"): "group" : _lst("<td>Circle</td>"),
data[key] = text.unescape(text.extract( "parody" : _lst("<td>Parody</td>"),
data[key], 'title="', '"')[0] or "") "tags" : _lst("<td>Contents</td>"),
"type" : _str("<td>Category</td>"),
data["gallery_id"] = text.parse_int(self.gallery_id) "characters": _lst("<td>Character</td>"),
data["title"] = info["title"] or info.get("j_title") or "" "collection": _str("<td>Collection</td>"),
data["title_en"] = info["title"] "language" : _str("<td>Language</td>"),
data["title_jp"] = info.get("j_title") or "" "scanlator" : _str("<td>Scanlator</td>"),
data["uploader"] = text.remove_html(data["uploader"]) "convention": _str("<td>Convention</td>"),
data["rating"] = text.parse_float(data["rating"]) "uploader" : text.remove_html(extr("<td>Uploader</td>", "</td>")),
"rating" : text.parse_float(extr(" :rating='" , "'")),
}
data["lang"] = util.language_to_code(data["language"]) data["lang"] = util.language_to_code(data["language"])
return data return data