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

[hentaihere] extract hmanga metadata

Browse Source
This commit is contained in:
Mike Fährmann
2017-09-20 12:26:53 +02:00
parent 04cc1ffe34
commit de174b40d6
1 changed files with 25 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
gallery_dl/extractor/hentaihere.py
View File

@@ -22,16 +22,35 @@ class HentaihereMangaExtractor(MangaExtractor):
test = [ test = [
("https://hentaihere.com/m/S13812", { ("https://hentaihere.com/m/S13812", {
"url": "d1ba6e28bb2162e844f8559c2b2725ba0a093559", "url": "d1ba6e28bb2162e844f8559c2b2725ba0a093559",
"keyword": "13c1ce7e15cbb941f01c843b0e89adc993d939ac",
}), }),
("https://hentaihere.com/m/S7608", { ("https://hentaihere.com/m/S7608", {
"url": "6c5239758dc93f6b1b4175922836c10391b174f7", "url": "6c5239758dc93f6b1b4175922836c10391b174f7",
"keyword": "675c7b7a4fa52cf569c283553bd16b4200a5cd36",
}), }),
] ]
def chapters(self, page): def chapters(self, page):
return list(text.extract_iter( results = []
page, '<li class="sub-chp clearfix">\n<a href="', '"' manga_id = int(self.url.rstrip("/").rpartition("/")[2][1:])
)) manga, pos = text.extract(
page, '<span itemprop="name">', '</span>')
mtype, pos = text.extract(
page, '<span class="mngType text-danger">[', ']</span>', pos)
while True:
url, pos = text.extract(
page, '<li class="sub-chp clearfix">\n<a href="', '"', pos)
if not url:
return results
chapter, pos = text.extract(page, 'title="Tagged: -">\n', '<', pos)
chapter_id, pos = text.extract(page, '/C', '"', pos)
chapter, _, title = text.unescape(chapter).strip().partition(" - ")
results.append((url, {
"manga_id": manga_id, "manga": manga, "type": mtype,
"chapter_id": int(chapter_id), "chapter": int(chapter),
"title": title, "lang": "en", "language": "English",
}))
class HentaihereChapterExtractor(hentaicdn.HentaicdnChapterExtractor): class HentaihereChapterExtractor(hentaicdn.HentaicdnChapterExtractor):
@@ -40,7 +59,7 @@ class HentaihereChapterExtractor(hentaicdn.HentaicdnChapterExtractor):
pattern = [r"(?:https?://)?(?:www\.)?hentaihere\.com/m/S(\d+)/(\d+)"] pattern = [r"(?:https?://)?(?:www\.)?hentaihere\.com/m/S(\d+)/(\d+)"]
test = [("https://hentaihere.com/m/S13812/1/1/", { test = [("https://hentaihere.com/m/S13812/1/1/", {
"url": "964b942cf492b3a129d2fe2608abfc475bc99e71", "url": "964b942cf492b3a129d2fe2608abfc475bc99e71",
"keyword": "7b31d19668b353f7be73b330a52ec6a7e56d23ea", "keyword": "a07753f655210525a80ff62607261715746f3273",
})] })]
def __init__(self, match): def __init__(self, match):
@@ -52,12 +71,14 @@ class HentaihereChapterExtractor(hentaicdn.HentaicdnChapterExtractor):
def get_job_metadata(self, page, images): def get_job_metadata(self, page, images):
title = text.extract(page, "<title>", "</title>")[0] title = text.extract(page, "<title>", "</title>")[0]
chapter_id = text.extract(page, 'report/C', '"')[0]
pattern = r"Page 1 \| (.+) \(([^)]+)\) - Chapter \d+: (.+) by (.+) at " pattern = r"Page 1 \| (.+) \(([^)]+)\) - Chapter \d+: (.+) by (.+) at "
match = re.match(pattern, title) match = re.match(pattern, title)
return { return {
"manga_id": self.gid, "manga_id": self.gid,
"manga": match.group(1), "manga": match.group(1),
"type": match.group(2), "type": match.group(2),
"chapter_id": chapter_id,
"chapter": self.chapter, "chapter": self.chapter,
"title": match.group(3), "title": match.group(3),
"author": match.group(4), "author": match.group(4),