From 97e7b25fbde303c2bcaaed42184447646153d2f0 Mon Sep 17 00:00:00 2001
From: Dantenerosas <solleo55@gmail.com>
Date: Sat, 30 Sep 2023 03:32:46 +0300
Subject: [PATCH] added yahoo parser

---
 src/parsers/Yahoo/yahoo_parser.py | 28 ++++++++++++++++++++++++++++
 src/parsers/base_parser.py        |  6 ++++--
 src/parsers/parser_mapping.py     |  3 ++-
 3 files changed, 34 insertions(+), 3 deletions(-)
 create mode 100644 src/parsers/Yahoo/yahoo_parser.py

diff --git a/src/parsers/Yahoo/yahoo_parser.py b/src/parsers/Yahoo/yahoo_parser.py
new file mode 100644
index 0000000..2c2861e
--- /dev/null
+++ b/src/parsers/Yahoo/yahoo_parser.py
@@ -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
diff --git a/src/parsers/base_parser.py b/src/parsers/base_parser.py
index a298099..d1f9aee 100644
--- a/src/parsers/base_parser.py
+++ b/src/parsers/base_parser.py
@@ -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
diff --git a/src/parsers/parser_mapping.py b/src/parsers/parser_mapping.py
index 5178c69..0c3f9d5 100644
--- a/src/parsers/parser_mapping.py
+++ b/src/parsers/parser_mapping.py
@@ -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,
     }
 )