added parsers for new social networks, rework master service

src/parsers/MyMail/my_mail_parser.py

@@ -0,0 +1,43 @@
+import os
+
+import requests
+from http.cookies import SimpleCookie
+
+from playwright.sync_api import Playwright
+from playwright.sync_api import sync_playwright
+
+from src.core.result import Result, ResultTypeEnum
+from src.parsers.base_parser import BaseParser
+
+
+class MyMailParser(BaseParser):
+    BASE_DIR = os.path.abspath(f"downloads/MyMailRu")
+
+    def get_video_link(self, playwright: Playwright):
+        browser = playwright.chromium.launch(headless=True)
+        context = browser.new_context()
+        page = context.new_page()
+        mobile_url = f"{self.params['link'][0:8]}m.{self.params['link'][8:]}"
+        page.goto(url=mobile_url)
+        link = page.get_attribute("xpath=//video", "src")
+        link = "https:" + link
+        title = page.locator("xpath=//div[@class='event-text__title']").text_content()
+        return link, title
+
+    def video_download(self, link: str = None, title: str = None):
+        if not link and not title:
+            with sync_playwright() as playwright:
+                link, title = self.get_video_link(playwright)
+
+        if os.path.exists(os.path.join(os.getcwd() + f"MyMailRu/{title}.mp4")):
+            return Result(result_type=ResultTypeEnum.EXIST)
+
+        rawdata = "searchuid=4515257701686610918; p=ki8AAAYkJdcA; act=064d11655c924c9f8f2aad0181a06a4b; o=:1763:AUAQ.m; oid=22SgCdFE5g2ZEFHy1FkYW; mrcu=5A5B64F228CC3AC265485FC5AE55; re_theme=system; re_theme_actual=dark; s=fver=0|rt=1|dpr=2|ww=1728|wh=963; ph_tp_horo-mail-ru=t=1|d=1693591768453; tmr_lvid=26ef811c203f1c0c0e5d1c8af1a4671b; tmr_lvidTS=1693591768481; _ym_uid=1693591769619458564; _ym_d=1693591769; ph_v_my-mail-ru=1; mrhc=CB75tAx8UrwCaiqE85YXWoCM2+CTT6/VsTcMdxv4iCM=; mr_my_b=1; _ga=GA1.2.2000378679.1694259228; mtrc=%7B%22mytrackerid%22%3A52867%2C%22tmr_lvid%22%3A%2226ef811c203f1c0c0e5d1c8af1a4671b%22%7D; c=FuoAZQEAsHsTAAAUAQgACQAAgLrElILY4CDYNvMTASDQrSUa; b=nUwAAJBoPmMDosXR5CCG5oQO4ltqxSBq54QOYpLl6yBiWW0VIvzl6zAOfNwNOtuHt6ADAAAIpgR06GAGp1YMpgB06AAA; i=AQAQDgNlCQATAAguDyABAYwDApADARgHAewHATwJAUMLARkUAXseAjAgAfUgAfYgAfcgAfggAfEiAZMCCHYnbgABAQIBAgIBBwIBCAIBCQIBDgIBDwIBEQIBEgIBFwIBGAIBUQUBVgUBaAUBdAUBdQUBoAUBoQUBpAUBpgUBqQUBegYBDgsBKQsBLgsBxQsBxwsByQsBzAsBzQsBcA0BdQ0BeA0BvQ0B6BAB6RAB6hABw2MB3AQIBAEBAAHhBAkBAeIECgQGB80HOgUIDQQqAgEACAELCAEeEAHWBggEAQEAAb0HCAQBoxUBiQ0FAgHz; video_key=192bed9054db7a4efa7943ad834c7a2e05a55237; VID=0eXAI6071-IK00000t1kP4oK:::0-0-a1b105a-9aaf457:CAASEL33YAsZEz357mCA71F8QJgacM9HfhwzMJ-j3X3e-iJIE0DIiLWfRhfTc3GgyUNfH8_EwadLkVinwp0LA-QyaRe9p0A_ZR0y1i9Hk8aVl8Q8ZB_Qd_hCZN_SfHmeOvHeoe6QBCvz5w2SHcI2iFuAXKJkJMvNuYwSeBLdWhCXvsK5M_M"
+        cookie = SimpleCookie()
+        cookie.load(rawdata)
+        cookies = {k: v.value for k, v in cookie.items()}
+
+        self.make_sure_path_exists()
+        video_response = requests.get(link, cookies=cookies)
+        with open(self.BASE_DIR + f"/{title}.mp4", "wb") as output:
+            output.write(video_response.content)

src/parsers/Yappy/yappy_parser.py

@@ -0,0 +1,33 @@
+import os
+
+import requests
+
+from bs4 import BeautifulSoup
+
+from src.core.result import ResultTypeEnum, Result
+from src.parsers.base_parser import BaseParser
+
+
+class YappyParser(BaseParser):
+    BASE_DIR = os.path.abspath(f"downloads/Yappy")
+
+    def get_video_link(self):
+        resp = requests.get(self.params["link"])
+        resp.encoding = self.BASE_ENCODING
+        soup = BeautifulSoup(resp.text, 'lxml')
+
+        link = soup.find('video').get("src")
+        title = soup.find('title').get_text()
+        return link, title
+
+    def video_download(self, link: str = None, title: str = None):
+        if not link and not title:
+            link, title = self.get_video_link()
+
+        if os.path.exists(os.path.join(os.getcwd() + f"Yappy/{title}.mp4")):
+            return Result(result_type=ResultTypeEnum.EXIST)
+
+        video_response = requests.get(link)
+        self.make_sure_path_exists()
+        with open(self.BASE_DIR + f"/{title}.mp4", "wb") as output:
+            output.write(video_response.content)

src/parsers/base_parser.py

@@ -0,0 +1,46 @@
+import errno
+import os
+
+from fastapi import HTTPException
+
+from src.core.result import ResultTypeEnum, Result
+from src.core.ydl import VideoDownloader
+from src.exceptions.download_exceptions import SiteNotImplementedException
+
+
+class BaseParser:
+    BASE_ENCODING = 'utf-8'
+    BASE_DIR = None
+
+    def __init__(self, params: dict):
+        self.params = params
+
+    def video_download(self):
+        ydl_opts = {
+            "format": self.params["format"],
+            "merge_output_format": self.params["merge_output_format"],
+            'outtmpl': self.params["outtmpl"],
+            "quiet": True
+        }
+        downloader = VideoDownloader(link=self.params["link"], ydl_opts=ydl_opts)
+        video_info = downloader.get_info()
+        if os.path.exists(
+                os.path.join(os.getcwd() + f"Youtube/{video_info['id']}_{video_info['width']}.{video_info['ext']}")
+        ):
+            return Result(result_type=ResultTypeEnum.EXIST)
+        try:
+            downloader.ydl_opts["quiet"] = False
+            result = downloader.download()
+            return result
+        except SiteNotImplementedException as ex:
+            raise HTTPException(
+                status_code=400,
+                detail=ex.message
+            )
+
+    def make_sure_path_exists(self,):
+        try:
+            os.makedirs(self.BASE_DIR)
+        except OSError as exception:
+            if exception.errno != errno.EEXIST:
+                raise