added yahoo parser

This commit is contained in:
Dantenerosas 2023-09-30 03:32:46 +03:00 committed by nikili0n
parent eb0a041de5
commit 97e7b25fbd
3 changed files with 34 additions and 3 deletions

View File

@ -0,0 +1,28 @@
import os
from playwright.sync_api import Playwright
from playwright.sync_api import sync_playwright
from src.parsers.base_parser import BaseParser
class YahooParser(BaseParser):
BASE_DIR = os.path.abspath(f"downloads/Yahoo")
def get_video_link(self, playwright: Playwright):
browser = playwright.chromium.launch(headless=True)
context = browser.new_context()
page = context.new_page()
page.goto(url=self.params["link"], wait_until='domcontentloaded')
link = page.get_attribute("xpath=//iframe", "src")
return link
def video_download(self, link: str = None, title: str = None):
base_link = self.params["link"]
with sync_playwright() as playwright:
link = self.get_video_link(playwright)
self.params["link"] = link
self.params['outtmpl'] = f"downloads/Yahoo/%(id)s_%(resolution)s.%(ext)s"
file_path = super().video_download()
self.params["link"] = base_link
return file_path

View File

@ -29,8 +29,10 @@ class BaseParser:
resolution = downloader.info['resolution']
else:
resolution = "NA"
path_to_video = f"{downloader.info['extractor_key']}/{downloader.info['id']}_{resolution}.{downloader.info['ext']}"
if "Yahoo" in ydl_opts["outtmpl"]["default"]:
path_to_video = f"Yahoo/{downloader.info['id']}_{resolution}.{downloader.info['ext']}"
else:
path_to_video = f"{downloader.info['extractor_key']}/{downloader.info['id']}_{resolution}.{downloader.info['ext']}"
if os.path.exists(os.path.join(os.getcwd() + "/downloads/" + path_to_video)):
raise FileAlreadyExistException(message=path_to_video)
downloader.ydl_opts["quiet"] = False

View File

@ -3,7 +3,7 @@ import re
from src.parsers.MyMail.my_mail_parser import MyMailParser
from src.parsers.Okru.ok_parser import OkParser
from src.parsers.Yappy.yappy_parser import YappyParser
from src.parsers.Yahoo.yahoo_parser import YahooParser
from src.parsers.base_parser import BaseParser
@ -22,6 +22,7 @@ parser_mapping = OrderedDict(
compile_regex(r"^dzen.ru/"): BaseParser,
compile_regex(r"^yappy.media/"): BaseParser,
compile_regex(r"^yandex.ru/"): BaseParser,
compile_regex(r"^.*\.yahoo.com/"): YahooParser,
compile_regex(r"^.*\.livejournal.com/"): BaseParser,
}
)