def _fetch_next_page(prev_link, content): match = re.search(r'<a href="(?P<next>[^">]*)".*?>Next', content) next_link = match.group('next') if match else '' if next_link: next_link = patch_url(prev_link, next_link) return next_link
def _fetch_next_page(prev_link, content): match = re.search(r'<a href="(?P<next>[^">]*)">(?:下一页|Next)', content) next_link = match.group("next") if match else "" if next_link: next_link = patch_url(prev_link, next_link) return next_link
def _fetch_next_page(prev_link, content): pattern = r'<a class="pn" href="(?P<next>[^"]*)" id="pnnext"' match = re.search(pattern, content) next_link = match.group('next') if match else '' if next_link: next_link = patch_url(prev_link, 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 _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): match = re.search(r'<a href="(?P<next>[^"]*)" class="n">下一页', content) next_link = match.group('next') if match else '' next_link = patch_url(prev_link, next_link) return next_link