def extract(self, target):
page = self.get_page(target)
if page is None:
return
logger.info('start to extract sub category in %s', target)
category_list = []
for category_item in page.find_all('li', 'category-item'):
for anchor in category_item.find_all('a'):
name = to_unicode(anchor.string)
if name is None:
name = to_unicode(name.strings)
name = re.sub(r'\xa0.+', '', name)
url = to_unicode(anchor['href'])
category_list.append((name, url))
write_csv(SUB_CATEGORY_CSV, 'ab', category_list)
logger.info('finished extracting sub category in %s', target)
def extract_top_category(self):
target = '/browse'
page = self.get_page(target)
if page is None:
return
logger.info('start to extract top category in %s', target)
category_url_list = []
for category_item in page.find_all('li', 'category-item'):
anchor = category_item.a
if anchor is None:
continue
category_name = to_unicode(anchor.string)
category_url = to_unicode(anchor['href'])
if category_name and category_url:
category_url_list.append((category_name, category_url))
if len(category_url_list) == 0:
logger.error('no category found')
return
write_csv(TOP_CATEGORY_CSV, 'wb', category_url_list)
logger.info("finished extracting top category into '%s'",
TOP_CATEGORY_CSV)
