def save_bangumi(data: WebsiteBangumi) -> None:
"""save bangumi to database"""
b, obj_created = Bangumi.get_or_create(keyword=data.keyword,
defaults=data.dict())
if not obj_created:
should_save = False
if data.cover and b.cover != data.cover:
b.cover = data.cover
should_save = True
if data.update_time != "Unknown" and data.update_time != b.update_time:
b.update_time = data.update_time
should_save = True
subtitle_group = Bangumi(
subtitle_group=data.subtitle_group).subtitle_group
if b.status != STATUS_UPDATING or b.subtitle_group != subtitle_group:
b.status = STATUS_UPDATING
b.subtitle_group = subtitle_group
should_save = True
if should_save:
b.save()
for subtitle_group in data.subtitle_group:
(Subtitle.insert({
Subtitle.id: str(subtitle_group.id),
Subtitle.name: str(subtitle_group.name),
}).on_conflict_replace()).execute()
def get_models(self) -> List[WebsiteBangumi]:
m = []
for s in self.scripts:
model = s.Model()
m.append(
WebsiteBangumi(
name=model.bangumi_name,
update_time=model.update_time,
keyword=model.bangumi_name,
cover=model.cover,
))
return m
def get_models(self) -> List[WebsiteBangumi]:
m = []
for s in self.scripts:
d = dict(s.Model())
m.append(
WebsiteBangumi(
name=d["bangumi_name"],
update_time=d["update_time"],
keyword=d["bangumi_name"],
cover=d["cover"],
))
return m
def fetch_single_bangumi(
self,
bangumi_id: str,
subtitle_list: Optional[List[str]] = None,
max_page: int = 0,
) -> Optional[WebsiteBangumi]:
html = get_text(server_root + f"Home/Bangumi/{bangumi_id}")
info = self.parse_bangumi_details_page(html)
return WebsiteBangumi(
name=info["name"],
keyword=bangumi_id,
status=info["status"],
update_time=info["update_time"],
subtitle_group=info["subtitle_group"],
episodes=parse_episodes(html, bangumi_id, subtitle_list),
)
def parser_day_bangumi(soup) -> List[WebsiteBangumi]:
"""
:param soup:
:type soup: bs4.Tag
"""
li = []
for soup in soup.find_all("li"):
url = soup.select_one("a")
span = soup.find("span")
if url:
name = url["title"]
url = url["href"]
bangumi_id = url.split("/")[-1]
soup.find("li")
li.append(
WebsiteBangumi(name=name,
keyword=bangumi_id,
cover=_COVER_URL + span["data-src"]))
return li
def parse_bangumi_with_week_days(
content, update_time, array_name
) -> List[WebsiteBangumi]:
r = re.compile(
array_name + "\\.push\\(\\['(.*?)','(.*?)','(.*?)','(.*?)','(.*?)'\\]\\)"
)
ret = r.findall(content)
bangumi_list = []
for bangumi_row in ret:
(cover_url, name, keyword, subtitle_raw, _) = bangumi_row
bangumi = WebsiteBangumi(keyword=keyword)
cover = re.findall("(/images/.*)$", cover_url)[0]
bs = BeautifulSoup(subtitle_raw, "html.parser")
a_list = bs.find_all("a")
for a in a_list:
subtitle_group_name = a.get_text(strip=True)
subtitle_group_id_raw = re.findall("team_id%3A(.+)$", a["href"])
if (len(subtitle_group_id_raw) == 0) or subtitle_group_name == "":
continue
subtitle_group_id = subtitle_group_id_raw[0]
bangumi.subtitle_group.append(
SubtitleGroup(id=subtitle_group_id, name=subtitle_group_name)
)
bangumi.name = name
bangumi.update_time = update_time
bangumi.keyword = keyword
bangumi.cover = SHARE_DMHY_URL + cover
# append to bangumi_list
bangumi_list.append(bangumi)
return bangumi_list
def fetch_bangumi_calendar(self) -> List[WebsiteBangumi]:
response = get_response(FETCH_URL)
if not response:
return []
bangumi_result = parser_bangumi(response)
return [WebsiteBangumi(**x) for x in bangumi_result]