def _fetch_next_page(prev_link, content):
q = urlparse.urlparse(prev_link).query
d = query2dict(q)
prev_page = d.get('page', '')
if prev_page:
match = re.search(r'<a href=(?P<next>[^">]*)>' + str(int(prev_page)+1) + r'</a>', content)
next_link = match.group('next') if match else ''
next_link = patch_url(prev_link, next_link)
else:
next_link = ''
return next_link
def _fetch_next_page(prev_link, content):
q = urlparse.urlparse(prev_link).query
d = query2dict(q)
prev_page = d.get('page', '')
if prev_page:
match = re.search(
r'<a href=(?P<next>[^">]*)>' + str(int(prev_page) + 1) +
r'</a>', content)
next_link = match.group('next') if match else ''
next_link = patch_url(prev_link, next_link)
else:
next_link = ''
return next_link
def _is_over_limit(self, link, limit):
q = urlparse.urlparse(link).query
d = query2dict(q)
return (int(d["p"]) * int(self.pmax)) <= limit
def _is_over_limit(self, link, limit):
q = urlparse.urlparse(link).query
d = query2dict(q)
return (int(d['pn']) + int(self.pmax)) <= limit