Files
gallery/gallery/painting/yandextv/parser.py
T
2026-10-05 20:46:04 +03:00

63 lines
2.6 KiB
Python

import datetime
from dataclasses import dataclass
from typing import Any
from bs4 import Tag
from gallery.sketch.parse.core import ParsedContext, ParseError
from gallery.sketch.parse.html import HTMLContextParser
from gallery.sketch.parse.json import JSONParser
from gallery.sketch.schedule.model import Channel, Schedule, ScheduleValue
from gallery.sketch.schedule.parse.category import CATEGORY_PARSER
from . import PROVIDER
@dataclass
class ScheduleData:
date: datetime.date
channel_id: str
data: str
class YandexTVScheduleParser(HTMLContextParser[ScheduleData, Schedule]):
def extract(self, data: ParsedContext[ScheduleData, Tag]) -> Schedule:
if data.data.select_one(".CheckboxCaptcha") is not None:
raise ParseError("Captcha")
values = []
channel_name = data.data.select_one(".channel-header__text").text.strip()
current_day = datetime.datetime.combine(data.context.date, datetime.datetime.min.time())
end = current_day + datetime.timedelta(days=1, hours=6)
prev_value: ScheduleValue | None = None
for item in data.data.select(".channel-schedule .channel-schedule__event"):
title = item.select_one(".channel-schedule__title").text.strip()
time_str = item.select_one(".channel-schedule__time").text.strip()
hours, minutes = map(int, time_str.split(":"))
item_date = current_day.replace(hour=hours, minute=minutes)
if prev_value is not None and item_date.hour < prev_value.start.hour:
current_day += datetime.timedelta(days=1)
item_date += datetime.timedelta(days=1)
live = item.select_one(".channel-schedule__info .icon_live") is not None
category = CATEGORY_PARSER.parse(title)
value = ScheduleValue(start=item_date, end=end, label=title, category=category, live=live)
values.append(value)
if prev_value is not None:
prev_value.end = item_date
prev_value = value
return Schedule(
channel=Channel(id=data.context.channel_id, name=channel_name, provider=PROVIDER),
date=data.context.date,
values=values,
)
class YandexTVChannelParser(JSONParser[list[Channel]]):
def extract(self, data: Any) -> list[Channel]:
_, values = data
result = []
for _, name, content in values:
if content["label"] == "Каналы":
channel_id = content["url"].split("/")[-1]
result.append(Channel(id=channel_id, name=name, provider=PROVIDER))
return result