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

[mangahere] support sub-chapters (e.g. ch4.5)

Browse Source
This commit is contained in:
Mike Fährmann
2015-11-28 00:31:04 +01:00
parent 88739a3564
commit 332d9e393b
1 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
gallery_dl/extractor/mangahere.py
View File

@@ -8,7 +8,7 @@
"""Extract manga pages from http://www.mangahere.co/""" """Extract manga pages from http://www.mangahere.co/"""
from .common import AsynchronousExtractor, Message from .common import Extractor, AsynchronousExtractor, Message
from .. import text from .. import text
import re import re
@@ -43,23 +43,22 @@ class MangaHereMangaExtractor(Extractor):
class MangaHereChapterExtractor(AsynchronousExtractor): class MangaHereChapterExtractor(AsynchronousExtractor):
category = "mangahere" category = "mangahere"
directory_fmt = ["{category}", "{manga}", "c{chapter:>03}"] directory_fmt = ["{category}", "{manga}", "c{chapter:>03}{chapter-minor}"]
filename_fmt = "{manga}_c{chapter:>03}_{page:>03}.{extension}" filename_fmt = "{manga}_c{chapter:>03}{chapter-minor}_{page:>03}.{extension}"
pattern = [r"(?:https?://)?(?:www\.)?mangahere\.co/manga/([^/]+(?:/v0*(\d+))?/c0*(\d+))"] pattern = [(r"(?:https?://)?(?:www\.)?mangahere\.co/manga/"
r"([^/]+(?:/v0*(\d+))?/c0*(\d+)(\.\d+)?)")]
url_fmt = "http://www.mangahere.co/manga/{}/{}.html" url_fmt = "http://www.mangahere.co/manga/{}/{}.html"
def __init__(self, match): def __init__(self, match):
AsynchronousExtractor.__init__(self) AsynchronousExtractor.__init__(self)
self.part = match.group(1) self.part, self.volume, self.chapter, self.chminor = match.groups()
self.volume = match.group(2)
self.chapter = match.group(3)
def items(self): def items(self):
page = self.request(self.url_fmt.format(self.part, 1)).text page = self.request(self.url_fmt.format(self.part, 1)).text
data = self.get_job_metadata(page) data = self.get_job_metadata(page)
yield Message.Version, 1 yield Message.Version, 1
yield Message.Directory, data.copy() yield Message.Directory, data.copy()
for i, url in zip(range(int(data["count"])), (self.get_image_urls(page))): for i, url in zip(range(int(data["count"])), self.get_image_urls(page)):
data["page"] = i+1 data["page"] = i+1
text.nameext_from_url(url, data) text.nameext_from_url(url, data)
yield Message.Url, url, data.copy() yield Message.Url, url, data.copy()
@@ -71,13 +70,14 @@ class MangaHereChapterExtractor(AsynchronousExtractor):
_ , pos = text.extract(page, '<select class="wid60"', '', pos) _ , pos = text.extract(page, '<select class="wid60"', '', pos)
_ , pos = text.extract(page, '</select>', '', pos) _ , pos = text.extract(page, '</select>', '', pos)
count, pos = text.extract(page, '>', '<', pos-30) count, pos = text.extract(page, '>', '<', pos-30)
manga = re.match(r"(.+) \d+ - Read .+ Chapter \d+ Online", manga).group(1) manga = re.match(r"(.+) \d+(\.\d+)? - Read .+ Chapter \d+(\.\d+)? Online", manga).group(1)
return { return {
"category": self.category, "category": self.category,
"manga": text.unescape(manga), "manga": text.unescape(manga),
# "title": TODO, # "title": TODO,
"volume": self.volume or "", "volume": self.volume or "",
"chapter": self.chapter, "chapter": self.chapter,
"chapter-minor": self.chminor or "",
"chapter-id": chid, "chapter-id": chid,
"count": count, "count": count,
"lang": "en", "lang": "en",