def get_one_page(weibo_id_str: str, page_id: int) -> list or None:
data = {'containerid': '107603' + weibo_id_str, 'page': page_id}
r = requests_get(url, data)
returned_json = r.json()
if not returned_json['ok']:
return None
weibo_cards = returned_json['data']['cards']
weibo_posts = []
for weibo_card in weibo_cards:
if weibo_card['card_type'] != 9:
continue
weibo_post_info = weibo_card['mblog']
# Skips sticky post
# TODO: return sticky post if it has not been saved
if weibo_post_info.get('isTop'):
continue
# Skips retweeted posts
# TODO: expect Jedi to forget about this
if weibo_post_info.get('retweeted_status'):
continue
# Processes long Weibo post
if weibo_post_info['isLongText']:
weibo_post_id_str: str = weibo_post_info['id']
weibo_post_info = get_long_weibo(weibo_post_id_str)
post = weibo.WeiboPost(weibo_post_info)
else:
post = weibo.WeiboPost(weibo_post_info)
weibo_posts.append(post)
return weibo_posts
def get_long_weibo(weibo_id_str: str) -> dict:
long_weibo_url = f'https://m.weibo.cn/detail/{weibo_id_str}'
html = requests_get(long_weibo_url).text
html = html[html.find('"status":'):]
html = html[:html.rfind('"hotScheme"')]
html = html[:html.rfind(',')]
html = '{' + html + '}'
returned_json = json.loads(html, strict=False)
return returned_json['status']
def get_user_info(user_id: int) -> dict or None:
data = {'containerid': '100505' + str(user_id)}
r = requests_get(url, data)
returned_json = r.json()
if not returned_json['ok']:
return None
info = returned_json['data']['userInfo']
if info.get('toolbar_menus'):
del info['toolbar_menus']
user_info = standardize_info(info)
return user_info