def parsed_post(posts):
for post in posts:
article = post.get('content') or ''
comments = post.get('comments') or []
imgs = self.parse_images(article) + flatten_lists([
self.parse_images(cmt.get('content', ''))
for cmt in comments
])
if len(imgs):
yield post, imgs
def parsed_post(posts):
for post in posts:
article = post.get('content') or ''
comments = post.get('comments') or []
imgs = self.parse_images(article) + flatten_lists([
self.parse_images(cmt.get('content', ''))
for cmt in comments
])
if len(imgs):
yield post, imgs
def get_metas(
self, num=30, sort='new', before=None, timebound=None,
callback=None):
logger.info('<%s> 開始取得看板內文章資訊', self.name)
paged_metas = self.api.get_metas(
self.name, sort, num, before, timebound)
buff = flatten_lists(metas for metas in paged_metas)
results = callback(buff) if callback else buff
logger.info('<%s> 資訊蒐集完成，共%d筆', self.name, len(buff))
return results
def extract_comments(self, comments):
return flatten_lists([cs.json() for cs in api.imap(comments)]) \
if not self.only_id and comments else comments