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

[readcomiconline] improve comic-page parsing

Browse Source
This commit is contained in:
Mike Fährmann
2018-12-30 13:13:25 +01:00
parent 0328a04a65
commit 259123732f
2 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
gallery_dl/extractor/readcomiconline.py
View File

@@ -20,7 +20,6 @@ class ReadcomiconlineBase():
filename_fmt = "{comic}_{issue:>03}_{page:>03}.{extension}" filename_fmt = "{comic}_{issue:>03}_{page:>03}.{extension}"
archive_fmt = "{issue_id}_{page}" archive_fmt = "{issue_id}_{page}"
root = "https://readcomiconline.to" root = "https://readcomiconline.to"
useragent = "Wget/1.19.2 (linux-gnu)"
request = cloudflare.request_func request = cloudflare.request_func
@@ -40,19 +39,22 @@ class ReadcomiconlineComicExtractor(ReadcomiconlineBase, MangaExtractor):
"keyword": "f5ba5246cd787bb750924d9690cb1549199bd516", "keyword": "f5ba5246cd787bb750924d9690cb1549199bd516",
}), }),
] ]
scheme = "https"
def __init__(self, match): def __init__(self, match):
MangaExtractor.__init__(self, match, self.root + match.group(1)) MangaExtractor.__init__(self, match, self.root + match.group(1))
self.session.headers["User-Agent"] = self.useragent
def chapters(self, page): def chapters(self, page):
results = [] results = []
comic, pos = text.extract(page, '<div class="heading"><h3>', '<') comic, pos = text.extract(page, ' class="barTitle">', '<')
page , pos = text.extract(page, '<ul class="list">', '</ul>', pos) page , pos = text.extract(page, ' class="listing">', '</table>', pos)
for item in text.extract_iter(page, '<a href="', '</span>'): comic = comic.rpartition("information")[0].strip()
url, _, issue = item.partition('"><span>') needle = ' title="Read {} '.format(comic)
comic = text.unescape(comic)
for item in text.extract_iter(page, ' href="', ' comic online '):
url, _, issue = item.partition(needle)
url = url.rpartition('"')[0]
if issue.startswith('Issue #'): if issue.startswith('Issue #'):
issue = issue[7:] issue = issue[7:]
results.append((self.root + url, { results.append((self.root + url, {
@@ -76,7 +78,6 @@ class ReadcomiconlineIssueExtractor(ReadcomiconlineBase, ChapterExtractor):
def __init__(self, match): def __init__(self, match):
ChapterExtractor.__init__(self, self.root + match.group(1)) ChapterExtractor.__init__(self, self.root + match.group(1))
self.issue_id = match.group(2) self.issue_id = match.group(2)
self.session.headers["User-Agent"] = self.useragent
def get_metadata(self, page): def get_metadata(self, page):
comic, pos = text.extract(page, " - Read\r\n ", "\r\n") comic, pos = text.extract(page, " - Read\r\n ", "\r\n")

1
test/test_results.py
View File

@@ -24,7 +24,6 @@ TRAVIS_SKIP = {
# temporary issues, etc. # temporary issues, etc.
BROKEN = { BROKEN = {
"deviantart", "deviantart",
"readcomiconline",
} }