def parse_index(self,page,url):
link_wrap_list = txt_wrap_by_all('已翻译','<span',page)
link_list = []
for link_wrap in link_wrap_list:
url = txt_wrap_by('href="','"',link_wrap)
if url and not url_is_fetched(url):
yield self.parse_page,'http://dongxi.net/%s'%url
def parse_index(self,page, url):
print "!"
link_wrapper_list = txt_wrap_by_all('<h5 clas', '</h5', page)
link_list = []
for link_wrapper in link_wrapper_list:
url = txt_wrap_by('href="', '"', link_wrapper)
filename = self.name_builder(url)
if not url_is_fetched(url):
yield self.save_page, url
else:
self.parse_page(filename)
