def getChapterUrls(self):
feedback.debug("domain: " + str(self.domain))
doc = self.getDomObject()
obj_a = doc.cssselect("a")
urls = []
for item in obj_a:
if not "href" in item.attrib.keys():
continue
m = re.match(
"""(//%s/manga/%s/[^"]+)""" % (self.domain, self.name),
item.attrib["href"])
if not m:
continue
target_url = "http:" + m.group(1)
if not target_url in urls:
urls.append(target_url)
if len(urls) < 1:
raise ComicEngine.ComicError("No URLs returned from %s" % self.url)
util.naturalSort(urls, ".+/c([0-9.]+)/")
# I've seen one series which was a load of "chapter 1" in different volumes... how to deal with that ?
feedback.debug(urls)
return urls
def getPageUrls(self):
doc = self.getDomObject()
options = doc.cssselect("#selectpage select option")
urls = []
for opt in options:
path = opt.attrib["value"]
urls.append("http://%s%s" % (self.domain, path))
util.naturalSort(urls, ".+/([0-9]+)$")
return urls
def getChapterUrls(self):
doc = self.getDomObject()
chapters = doc.get_element_by_id("chapterlist").cssselect("tr td a")
urls = []
for chap in chapters:
link = chap.attrib["href"]
chapter_num = util.regexGroup("/%s/([0-9.]+)$" % self.name, link)
if chapter_num:
urls.append("%s/%s" % (self.url, chapter_num))
util.naturalSort(urls)
return urls
def getChapterUrls(self):
dom = self.getDomObject()
chapters = dom.get_element_by_id("chapterlist").cssselect("td a")
urls = []
for elem_a in chapters:
path = elem_a.attrib['href']
if re.match("/%s/[0-9.]+" % self.name, path):
urls.append("https://%s%s" % (self.domain, path))
util.naturalSort(urls, ".+/([0-9.]+)$")
return urls
def getChapterUrls(self):
dom = self.getDomObject()
alinks = dom.cssselect("table tr td a")
chaplinks = []
for elem_a in alinks:
href = elem_a.attrib['href']
if re.match("/r/%s" % self.name, href):
chaplinks.append("https://readms.net"+href)
util.naturalSort(chaplinks, ".+/%s/([0-9.]+)/.+")
return chaplinks
def getPageUrls(self):
doc = self.getDomObject()
div = doc.get_element_by_id("top_chapter_list").getparent()
options = div.cssselect("select option")
urls = []
for opt in options:
pagenum = opt.text_content()
if re.match("^[0-9]+$", pagenum):
urls.append("%s/%i.html" % (self.url, int(pagenum)))
util.naturalSort(urls)
return urls
def getChapterUrls(self):
doc = self.getDomObject()
chapter_links = doc.cssselect("li span a")
urls = []
for a in chapter_links:
if "href" not in a.attrib.keys():
continue
link = a.attrib['href']
if re.match("//.+?/manga/[^/]+/c[0-9.]+/", link):
urls.append("http:" + link)
util.naturalSort(urls)
return urls
def getPageUrls(self):
doc = self.getDomObject()
top_bar = doc.get_element_by_id("top_bar")
#options = top_bar.get_elements_by_tag_name("option")
options = top_bar.cssselect("option")
urls = []
base_url = self.getBaseChapterUrl()
for option in options:
m = re.match("^[0-9]+$", option.attrib["value"])
if not m:
continue
v = int(m.group(0))
if v < 1:
continue
urls.append("%s/%i.html" % (base_url, v))
util.naturalSort(urls, ".+/([0-9.]+)\\.html")
return urls