def list_chapters(self, data):
url = self.get_series_url(data)
content = urlretrieve(url)
doc = ET.HTML(content)
chapters = self._list_chapters(doc)
pages = set([n.attrib['href'] \
for n in doc.xpath("//ul[@class='pgg']/li/a")])
for url in pages:
content = urlretrieve(url)
doc = ET.HTML(content)
chapters += self._list_chapters(doc)
chapters.sort(lambda a, b: smart_cmp(a['chapter_label'], b['chapter_label']))
return chapters
def list_chapters(self, data):
url = self.get_series_url(data)
content = urlretrieve(url)
doc = ET.HTML(content)
chapters = self._list_chapters(doc)
pages = [self.baseurl+n.attrib['href'] \
for n in filter(lambda n: n.attrib['href'].startswith('/series/'),
doc.xpath("//div[@class='pagenav']/div/a"))]
for url in pages:
content = urlretrieve(url)
doc = ET.HTML(content)
chapters += self._list_chapters(doc)
chapters.sort(lambda a, b: smart_cmp(a['chapter_label'], b['chapter_label']))
return chapters
def list_chapters(self, data):
url = self.get_series_url(data)
content = urlretrieve(url)
doc = ET.HTML(content)
chapters = self._list_chapters(doc)
pages = [self.baseurl+n.attrib['href'] \
for n in filter(lambda n: n.attrib['href'].startswith('/search.php?series='),
doc.xpath("//a"))]
for url in pages:
content = urlretrieve(url)
doc = ET.HTML(content)
chapters += self._list_chapters(doc)
chapters.sort(lambda a, b: smart_cmp(a['chapter'], b['chapter']))
return chapters
def list_chapters(self, data):
url = self.get_series_url(data)
content = urlretrieve(url)
doc = ET.HTML(content)
chapters = self._list_chapters(doc)
pages = set([n.attrib['href'] \
for n in doc.xpath("//ul[@class='pgg']/li/a")])
for url in pages:
content = urlretrieve(url)
doc = ET.HTML(content)
chapters += self._list_chapters(doc)
chapters.sort(
lambda a, b: smart_cmp(a['chapter_label'], b['chapter_label']))
return chapters
