def parse_reply(item: BeautifulSoup):
users = []
for u in item.find_all("a",
attrs={
"class": "tshuz_at",
"target": "_blank"
}):
users.append(
User(process_html_string(u.get_text()),
User.extract_uid(u.get("href"))))
if len(users) < 1:
raise Exception("Can't find user information")
content = process_html_string(
item.find("span", attrs={
"class": "tshuz_cnt_main"
}).get_text())
tick = item.find("div", attrs={
"class": "tshuz_time"
}).find("span").get("title")
return Reply(users[0],
content=content,
tick=tick,
user_to=users[1] if len(users) >= 2 else None)
def parse_content_text(item):
content = item.find("td", attrs={"class": "t_f"})
if content is None:
content = item.find("div", attrs={"class": "t_f"})
if content is None:
raise Exception("Can't find content container in item block.")
# Remove no permission tip and image text tip
remove_list = content.find_all(
"div", attrs={"class": "attach_nopermission attach_tips"})
if remove_list is not None:
[s.extract() for s in remove_list]
remove_list = content.find_all("div",
attrs={"class": "tip tip_4 aimg_tip"})
if remove_list is not None:
[s.extract() for s in remove_list]
return process_html_string(content.get_text())
def parse_user(a_tag):
return User(name=process_html_string(a_tag.get_text()),
uid=User.extract_uid(a_tag.get("href")))
def comments(self):
return [process_html_string(c.get_text()) for c in self.content_list]