def get_images(self, chapter_url: str) -> 'List[str]':
soup = BeautifulSoup(self.get_str(chapter_url), 'html.parser')
opts = soup.find('select', class_='wid60').find_all('option')
return [
'http:' + opt['value'] for opt in opts
if get_text(opt) != 'Featured'
]
def get_chapters(self, manga_url: str) -> 'List[Chapter]':
soup = BeautifulSoup(self.get_str(manga_url), 'html.parser')
chapters = [
Chapter('', get_text(a), a['href'])
for a in soup.find('ul', class_='chapters').find_all('a')
]
chapters.reverse()
return chapters
def get_chapters(self, manga_url: str) -> 'List[Chapter]':
soup = BeautifulSoup(self.get_str(manga_url), 'html.parser')
chapters = [
Chapter('', get_text(a), self.site_url + a['href'])
for a in soup.find('table', id='listing').find_all('a')
]
# don't need to use `chapters.reverse()` here
return chapters
def get_chapters(self, manga_url: str) -> 'List[Chapter]':
soup = BeautifulSoup(self.get_str(manga_url), 'html.parser')
ulist = soup.find('div', class_='detail_list').ul
chapters = [
Chapter('', get_text(a), 'http:' + a['href'])
for a in ulist.find_all('a')
]
chapters.reverse()
return chapters
def get_chapters(self, manga_url: str) -> 'List[Chapter]':
soup = BeautifulSoup(self.get_str(manga_url), 'html.parser')
div = soup.find('div', class_='chapter-list')
chapters = []
for anchor in div.find_all('a'):
if anchor['href'].startswith('/'):
anchor['href'] = 'https:' + anchor['href']
chapters.append(Chapter('', get_text(anchor), anchor['href']))
chapters.reverse()
return chapters
def search(self, manga: str) -> 'List[Manga]':
# TODO: find a better way to do this:
url = '{}/buscar/{}.html'.format(self.site_url, quote_plus(manga))
# page restriction: len(manga) must to be >= 4
soup = BeautifulSoup(self.get_str(url), 'html.parser')
divs = soup.find_all('div', class_='cont_manga')
return [
Manga('', get_text(div.a.header), div.a['href'], self.name)
for div in divs
]
def search(self, manga: str) -> 'List[Manga]':
url = self.site_url + "/search/"
soup = BeautifulSoup(self.get_str(url, {'wd': manga}), 'html.parser')
direlist = soup.find('ul', class_='direlist')
results = [
Manga('', get_text(a), a['href'], self.name)
for a in direlist.find_all('a', class_='bookname')
] # type: List[Manga]
pagelist = soup.find('ul', class_='pagelist')
if pagelist:
# this get only first few pages:
for page in pagelist.find_all('a')[1:-1]:
soup = BeautifulSoup(self.get_str(page['href']), 'html.parser')
direlist = soup.find('ul', class_='direlist')
anchors = direlist.find_all('a', class_='bookname')
results.extend(
Manga('', get_text(a), a['href'], self.name)
for a in anchors)
return results
def search(self, manga: str) -> 'List[Manga]':
query_str = ''
for char in manga:
if char.isalnum():
query_str += char
else:
query_str += ' '
query_str = '_'.join(query_str.split())
req_data = {'search_style': 'tentruyen', 'searchword': query_str}
url = self.site_url + '/home_json_search/'
res_data = self.get_json(url, req_data,
method='POST') # type: List[dict]
return [
Manga('', get_text(BeautifulSoup(result['name'], 'html.parser')),
self.site_url + '/manga/' + result['nameunsigned'],
self.name) for result in res_data
]