Add Mixdrop, Maxstream, okru . Vixcloud fix

mediaflow_proxy/extractors/maxstream.py

@@ -0,0 +1,71 @@
+import re
+import string
+from typing import Dict, Any
+from bs4 import BeautifulSoup
+
+from mediaflow_proxy.extractors.base import BaseExtractor, ExtractorError
+
+
+class MaxstreamExtractor(BaseExtractor):
+    """Maxstream URL extractor."""
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.mediaflow_endpoint = "hls_manifest_proxy"
+
+    async def get_uprot(self, link: str):
+        """Extract MaxStream URL."""
+        if "msf" in link:
+            link = link.replace("msf", "mse")
+        response = await self._make_request(link)
+        soup = BeautifulSoup(response.text, "lxml")
+        maxstream_url = soup.find("a")
+        maxstream_url = maxstream_url.get("href")
+        return maxstream_url
+
+    async def extract(self, url: str, **kwargs) -> Dict[str, Any]:
+        """Extract Maxstream URL."""
+        maxstream_url = await self.get_uprot(url)
+        response = await self._make_request(maxstream_url, headers={"accept-language": "en-US,en;q=0.5"})
+
+        # Extract and decode URL
+        match = re.search(r"\}\('(.+)',.+,'(.+)'\.split", response.text)
+        if not match:
+            raise ExtractorError("Failed to extract URL components")
+
+        s1 = match.group(2)
+        # Extract Terms
+        terms = s1.split("|")
+        urlset_index = terms.index("urlset")
+        hls_index = terms.index("hls")
+        sources_index = terms.index("sources")
+        result = terms[urlset_index + 1 : hls_index]
+        reversed_elements = result[::-1]
+        first_part = terms[hls_index + 1 : sources_index]
+        reversed_first_part = first_part[::-1]
+        first_url_part = ""
+        for first_part in reversed_first_part:
+            if "0" in first_part:
+                first_url_part += first_part
+            else:
+                first_url_part += first_part + "-"
+
+        base_url = f"https://{first_url_part}.host-cdn.net/hls/"
+        if len(reversed_elements) == 1:
+            final_url = base_url + "," + reversed_elements[0] + ".urlset/master.m3u8"
+        lenght = len(reversed_elements)
+        i = 1
+        for element in reversed_elements:
+            base_url += element + ","
+            if lenght == i:
+                base_url += ".urlset/master.m3u8"
+            else:
+                i += 1
+        final_url = base_url
+
+        self.base_headers["referer"] = url
+        return {
+            "destination_url": final_url,
+            "request_headers": self.base_headers,
+            "mediaflow_endpoint": self.mediaflow_endpoint,
+        }

mediaflow_proxy/extractors/mixdrop.py

@@ -10,6 +10,8 @@ class MixdropExtractor(BaseExtractor):
 
     async def extract(self, url: str, **kwargs) -> Dict[str, Any]:
         """Extract Mixdrop URL."""
+        if "club" in url:
+            url = url.replace("club", "ps").split("/2")[0]
         response = await self._make_request(url, headers={"accept-language": "en-US,en;q=0.5"})
 
         # Extract and decode URL

mediaflow_proxy/extractors/okru.py

@@ -0,0 +1,33 @@
+import re
+from bs4 import BeautifulSoup, SoupStrainer
+import json
+
+from typing import Dict, Any
+
+from mediaflow_proxy.extractors.base import BaseExtractor, ExtractorError
+
+
+class OkruExtractor(BaseExtractor):
+    """Okru URL extractor."""
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.mediaflow_endpoint = "hls_manifest_proxy"
+
+    async def extract(self, url: str, **kwargs) -> Dict[str, Any]:
+        """Extract Okru URL."""
+        response = await self._make_request(url)
+        soup = BeautifulSoup(response.text, "lxml", parse_only=SoupStrainer("div"))
+        if soup:
+            div = soup.find("div", {"data-module": "OKVideo"})
+            data_options = div.get("data-options")
+            data = json.loads(data_options)
+            metadata = json.loads(data["flashvars"]["metadata"])
+            final_url = metadata["hlsMasterPlaylistUrl"]
+
+            self.base_headers["referer"] = url
+            return {
+                "destination_url": final_url,
+                "request_headers": self.base_headers,
+                "mediaflow_endpoint": self.mediaflow_endpoint,
+            }

mediaflow_proxy/extractors/vixcloud.py

@@ -4,6 +4,7 @@ from bs4 import BeautifulSoup, SoupStrainer
 from mediaflow_proxy.extractors.base import BaseExtractor, ExtractorError
 import json
 from urllib.parse import urlparse, parse_qs
+from urllib.parse import urlparse, parse_qs
 
 
 class VixCloudExtractor(BaseExtractor):