Merge pull request #284 from nikhilbadyal/feature/280-use-beautifulsoup4-for-scrapping

🎨 Use BS4 for scrapping

requirements.txt

@@ -4,5 +4,4 @@ lastversion==3.0.1
 loguru==0.7.0
 pre-commit==3.3.3
 requests==2.31.0
-selectolax==0.3.16
 tqdm==4.66.1

src/downloader/apkmirror.py

@@ -1,62 +1,84 @@
 """Downloader Class."""
-import re
 from typing import Any
 
+import requests
+from bs4 import BeautifulSoup
 from loguru import logger
-from selectolax.lexbor import LexborHTMLParser
 
+from scripts.status_check import headers
 from src.downloader.download import Downloader
 from src.exceptions import AppNotFound
+from src.utils import apkmirror_status_check, bs4_parser
 
 
 class ApkMirror(Downloader):
     """Files downloader."""
 
-    def extract_download_link(self, page: str, app: str) -> None:
+    def _extract_force_download_link(self, link: str, app: str) -> None:
+        """Extract force download link."""
+        r = requests.get(link, headers=headers)
+        if r.status_code != 200:
+            raise AppNotFound(f"Unable to connect with {link} on ApkMirror.")
+        soup = BeautifulSoup(r.text, bs4_parser)
+        notes_divs = soup.find(class_="tab-pane")
+        possible_links = notes_divs.find_all("a")
+        for possible_link in possible_links:
+            if possible_link.get("href") and "download.php?id=" in possible_link.get(
+                "href"
+            ):
+                return self._download(
+                    self.config.apk_mirror + possible_link["href"], f"{app}.apk"
+                )
+        raise AppNotFound(f"Unable to download apk from {link}")
+
+    def extract_download_link(self, main_page: str, app: str) -> None:
         """Function to extract the download link from apkmirror html page.
 
-        :param page: Url of the page
+        :param main_page: Url of the page
         :param app: Name of the app
         """
-        logger.debug(f"Extracting download link from\n{page}")
-        parser = LexborHTMLParser(self.config.session.get(page).text)
-
-        resp = self.config.session.get(
-            self.config.apk_mirror + parser.css_first("a.accent_bg").attributes["href"]
+        logger.debug(f"Extracting download link from\n{main_page}")
+        r = requests.get(main_page, headers=headers)
+        if r.status_code != 200:
+            raise AppNotFound(f"Unable to connect with {main_page} on ApkMirror.")
+        soup = BeautifulSoup(r.text, bs4_parser)
+        download_button = soup.find(class_="center")
+        download_links = download_button.find_all("a")
+        final_download_link = None
+        for download_link in download_links:
+            if download_link.get("href"):
+                if "download/?key=" in download_link.get("href"):
+                    final_download_link = download_link["href"]
+                    break
+        if not final_download_link:
+            raise AppNotFound(f"Unable to download apk from {main_page}")
+        self._extract_force_download_link(
+            self.config.apk_mirror + final_download_link, app
         )
-        parser = LexborHTMLParser(resp.text)
 
-        href = parser.css_first(
-            "p.notes:nth-child(3) > span:nth-child(1) > a:nth-child(1)"
-        ).attributes["href"]
-        self._download(self.config.apk_mirror + href, f"{app}.apk")
-
-    def get_download_page(self, parser: LexborHTMLParser, main_page: str) -> str:
+    def get_download_page(self, main_page: str) -> str:
         """Function to get the download page in apk_mirror.
 
         :param parser: Parser
         :param main_page: Main Download Page in APK mirror(Index)
         :return:
         """
-        logger.debug(f"Getting download page from {main_page}")
-        apm = parser.css(".apkm-badge")
-        sub_url = ""
-        for is_apm in apm:
-            parent_text = is_apm.parent.parent.text()
-            if "APK" in is_apm.text() and (
-                "arm64-v8a" in parent_text
-                or "universal" in parent_text
-                or "noarch" in parent_text
-            ):
-                parser = is_apm.parent
-                sub_url = parser.css_first(".accent_color").attributes["href"]
+        r = requests.get(main_page, headers=headers)
+        if r.status_code != 200:
+            raise AppNotFound(f"Unable to connect with {main_page} on ApkMirror.")
+        soup = BeautifulSoup(r.text, bs4_parser)
+        list_widget = soup.find(class_="listWidget")
+        table_rows = list_widget.find_all(class_="table-row")
+        sub_url = None
+        for row in table_rows:
+            if row.find(class_="accent_color"):
+                apk_type = row.find(class_="apkm-badge").get_text()
+                if apk_type == "APK":
+                    sub_url = row.find(class_="accent_color")["href"]
                     break
-        if sub_url == "":
-            logger.exception(
-                f"Unable to find any apk on apkmirror_specific_version on {main_page}"
-            )
-            raise AppNotFound("Unable to find apk on apkmirror site.")
-        return self.config.apk_mirror + sub_url
+        if not sub_url:
+            raise AppNotFound("Unable to download apk from APKMirror.")
+        return f"{self.config.apk_mirror}{sub_url}"
 
     def specific_version(self, app: str, version: str) -> None:
         """Function to download the specified version of app from  apkmirror.
@@ -67,10 +89,7 @@ class ApkMirror(Downloader):
         """
         version = version.replace(".", "-")
         main_page = f"{self.config.apk_mirror_version_urls.get(app)}-{version}-release/"
-        parser = LexborHTMLParser(
-            self.config.session.get(main_page, allow_redirects=True).text
-        )
-        download_page = self.get_download_page(parser, main_page)
+        download_page = self.get_download_page(main_page)
         self.extract_download_link(download_page, app)
 
     def latest_version(self, app: str, **kwargs: Any) -> None:
@@ -80,24 +99,14 @@ class ApkMirror(Downloader):
         :param app: Name of the application
         :return: Version of downloaded apk
         """
-        logger.debug(f"Trying to download {app}'s latest version from apkmirror")
-        page = self.config.apk_mirror_urls.get(app)
-        if not page:
-            logger.debug("Invalid app")
-            raise AppNotFound("Invalid app")
-        parser = LexborHTMLParser(self.config.session.get(page).text)
-        try:
-            main_page = parser.css_first(".appRowVariantTag>.accent_color").attributes[
-                "href"
-            ]
-        except AttributeError:
-            # Handles a case when variants are not available
-            main_page = parser.css_first(".downloadLink").attributes["href"]
-        match = re.search(r"\d", main_page)
-        if not match:
-            logger.error("Cannot find app main page")
-            raise AppNotFound()
-        main_page = f"{self.config.apk_mirror}{main_page}"
-        parser = LexborHTMLParser(self.config.session.get(main_page).text)
-        download_page = self.get_download_page(parser, main_page)
-        self.extract_download_link(download_page, app)
+        from src.patches import Patches
+
+        package_name = Patches.get_package_name(app)
+        response = apkmirror_status_check(package_name)
+        if response["data"][0]["exists"]:
+            version = response["data"][0]["release"]["version"]
+            logger.debug(
+                f"Trying to download {app}'s latest version({version}) from apkmirror"
+            )
+            return self.specific_version(app, version)
+        raise AppNotFound("App not found on apkmirror.")

src/downloader/apksos.py

@@ -1,10 +1,13 @@
 """APK SOS Downloader Class."""
 from typing import Any
 
-from loguru import logger
-from selectolax.lexbor import LexborHTMLParser
+import requests
+from bs4 import BeautifulSoup
 
+from scripts.status_check import headers
 from src.downloader.download import Downloader
+from src.exceptions import AppNotFound
+from src.utils import bs4_parser
 
 
 class ApkSos(Downloader):
@@ -16,13 +19,14 @@ class ApkSos(Downloader):
         :param page: Url of the page
         :param app: Name of the app
         """
-        parser = LexborHTMLParser(self.config.session.get(page).text)
-        download_url = parser.css_first(
-            r"body > div > div > div > div > div.col-sm-12.col-md-8 > div.card.fluid.\.idma > "
-            "div.section.row > div.col-sm-12.col-md-8.text-center > p > a"
-        ).attributes["href"]
-        self._download(download_url, f"{app}.apk")
-        logger.debug(f"Downloaded {app} apk from apk_combo_downloader in rt")
+        r = requests.get(page, headers=headers, allow_redirects=True)
+        soup = BeautifulSoup(r.text, bs4_parser)
+        download_button = soup.find(class_="col-sm-12 col-md-8 text-center")
+        possible_links = download_button.find_all("a")
+        for possible_link in possible_links:
+            if possible_link.get("href"):
+                return self._download(possible_link["href"], f"{app}.apk")
+        raise AppNotFound("Unable to download apk from apk_combo")
 
     def latest_version(self, app: str, **kwargs: Any) -> None:
         """Function to download whatever the latest version of app from

src/downloader/uptodown.py

@@ -1,10 +1,11 @@
 """Upto Down Downloader."""
 from typing import Any
 
+import requests
 from bs4 import BeautifulSoup
 from loguru import logger
-from selectolax.lexbor import LexborHTMLParser
 
+from scripts.status_check import headers
 from src.downloader.download import Downloader
 from src.exceptions import AppNotFound
 from src.utils import bs4_parser
@@ -14,9 +15,12 @@ class UptoDown(Downloader):
     """Files downloader."""
 
     def extract_download_link(self, page: str, app: str) -> None:
-        parser = LexborHTMLParser(self.config.session.get(page).text)
-        main_page = parser.css_first("#detail-download-button")
-        download_url = main_page.attributes["data-url"]
+        r = requests.get(page, headers=headers, allow_redirects=True)
+        soup = BeautifulSoup(r.text, bs4_parser)
+        soup = soup.find(id="detail-download-button")
+        download_url = soup.get("data-url")
+        if not download_url:
+            raise AppNotFound("Unable to download from uptodown.")
         self._download(download_url, f"{app}.apk")
         logger.debug(f"Downloaded {app} apk from upto_down_downloader in rt")