feat: snaptik slideshow

pyproject.toml

@@ -0,0 +1,25 @@
+[tool.poetry]
+name = "tiktok-downloader"
+version = "0.1.0"
+description = "tiktok downloader"
+authors = ["krypton-byte <[email protected]>"]
+license = "GPL-3.0"
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.11"
+bs4 = "^0.0.1"
+flask = "^3.0.0"
+cloudscraper = "^1.2.71"
+requests = "^2.31.0"
+tqdm = "^4.66.1"
+rich = "^13.7.0"
+httpx = "^0.25.2"
+aiohttp = "^3.9.1"
+moviepy = "^1.0.3"
+js2py = "^0.74"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

requirements.txt

@@ -5,4 +5,6 @@ requests
 tqdm
 rich
 httpx
-aiohttp
+aiohttp
+moviepy
+pyjsparser

tiktok_downloader/Except.py

@@ -1,2 +1,5 @@
 class InvalidUrl(Exception):
     pass
+
+class NoImageToSlideshow(Exception):
+    pass

tiktok_downloader/snaptik.py

@@ -1,7 +1,10 @@
+import re
+from bs4 import BeautifulSoup
 from httpx import AsyncClient
 from sys import stderr
 from ast import literal_eval
-from .utils import Download, DownloadAsync
+import pyjsparser
+from .utils import Download, DownloadAsync, Type, extension_to_type
 from .Except import InvalidUrl
 from requests import Session
 from re import findall
@@ -11,141 +14,140 @@
 
 
 class Snaptik(Session):
-    '''
+    """
     :param tiktok_url:
     ```python
     >>> tik=snaptik('url')
     >>> tik.get_media()
     [<[type:video]>, <[type:video]>]
     ```
-    '''
+    """
 
     def __init__(self, tiktok_url: str) -> None:
         super().__init__()
         self.headers: dict[str, str] = {
-            'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) '
-                          'AppleWebKit/537.36 (KHTML, like Gecko) '
-                          'Chrome/86.0.4240.111 Safari/537.36'
+            "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) "
+            "AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/86.0.4240.111 Safari/537.36"
         }
         self.tiktok_url = tiktok_url
 
+    def render(self, token, interval: int = 1):
+        result = self.get('https://snaptik.app/render.php', params={'token': token}).json()
+        while True:
+            resp = self.get("https://snaptik.app/task.php", params={'token': result['task_id']}).json()
+            if resp['progress'] == 100:
+                return Download(resp['download_url'], self, Type.VIDEO) 
+
     def get_media(self) -> list[Download]:
-        '''
+        """
         ```python
         >>> <snaptik object>.get_media()
         [<[type:video]>, <[type:video]>]
         ```
-        '''
+        """
+        result = []
         resp = cloudscraper.create_scraper().get(
-            'https://snaptik.app/abc2.php',
+            "https://snaptik.app/abc2.php",
             params={
-                'url': self.tiktok_url,
-                'lang': 'en',
+                "url": self.tiktok_url,
+                "lang": "en",
                 **dict(
                     findall(
                         'name="(token)" value="(.*?)"',
-                        self.get('https://snaptik.app/en').text))}
+                        self.get("https://snaptik.app/en").text,
+                    )
+                ),
+            },
         )
-        if 'error_api_web;' in resp.text or 'Error:' in resp.text:
+        if "error_api_web;" in resp.text or "Error:" in resp.text:
             raise InvalidUrl()
         stderr.flush()
-        dec = decoder(*literal_eval(
-            findall(
-                r'\(\".*?,.*?,.*?,.*?,.*?.*?\)',
-                resp.text
-            )[0]
-        ))
-
-        stderr.flush()
-
-        current_url = urlparse(resp.url).scheme + "://" + urlparse(resp.url).netloc
-        links_list = [
-                i for i in findall(r'<a href=\\"(https?://[\w\./\-&?=]+)', dec)
-            ] + [
-                current_url + i.strip('\\') for i in findall(r'(/file.php?.*?)\"', dec)
+        dec = decoder(
+            *literal_eval(findall(r"\(\".*?,.*?,.*?,.*?,.*?.*?\)", resp.text)[0])
+        )
+        dec = pyjsparser.parse(re.sub(r"(async|await)", "", dec))["body"][0][
+            "consequent"
+        ]["body"][0]["consequent"]["body"][1]["expression"]["right"]["value"]
+        bs = BeautifulSoup(dec)
+        for vl in  bs.find_all("div", attrs={"class","video-links"}):
+            for a in vl.find_all("a"):
+                result.append(Download(a["href"] if a['href'].startswith('http') else 'https://snaptik.app' + a['href'], self, Type.VIDEO))
+            for button in vl.find_all("button"):
+                try:
+                    result.append(Download(button['data-backup'], self, Type.VIDEO))
+                except KeyError:
+                    result.append(Download('', self, Type.VIDEO, render=lambda invertal: self.render(button['data-token'])))
+        result.extend(
+            [
+                Download(obj["href"], self, Type.IMAGE)
+                for obj in bs.find_all(
+                    "a", attrs={"data-event": "download_albumPhoto_photo"}
+                )
             ]
-
-        # If our video is slideshow - download link will have "?type=dl", so let's move it to the 1 place
-        index_to_move = None
-        for index, link in enumerate(links_list):
-            if "?type=dl" in link:
-                index_to_move = index
-                break
-
-        # Move the link to the first position (0 index) if found
-        if index_to_move is not None:
-            links_list.insert(0, links_list.pop(index_to_move))
-
-        return [
-            Download(
-                i,
-                self
-            ) for i in links_list
-        ]
+        )
+        return result
 
     def __iter__(self):
         yield from self.get_media()
 
 
 class SnaptikAsync(AsyncClient):
-    '''
+    """
     :param tiktok_url:
     ```python
     >>> tik=snaptik('url')
     >>> tik.get_media()
     [<[type:video]>, <[type:video]>]
     ```
-    '''
+    """
 
     def __init__(self, tiktok_url: str) -> None:
         super().__init__()
         self.headers: dict[str, str] = {
-            'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) '
-                          'AppleWebKit/537.36 (KHTML, like Gecko) '
-                          'Chrome/86.0.4240.111 Safari/537.36'
+            "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) "
+            "AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/86.0.4240.111 Safari/537.36"
         }
         self.tiktok_url = tiktok_url
 
     async def get_media(self) -> list[DownloadAsync]:
-        '''
+        """
         ```python
         >>> <snaptik object>.get_media()
         [<[type:video]>, <[type:video]>]
         ```
-        '''
+        """
         resp = await self.get(
-            'https://snaptik.app/abc2.php',
+            "https://snaptik.app/abc2.php",
             params={
-                'url': self.tiktok_url,
-                'lang': 'en',
+                "url": self.tiktok_url,
+                "lang": "en",
                 **dict(
                     findall(
                         'name="(token)" value="(.*?)"',
-                        (await self.get('https://snaptik.app/en')).text))},
+                        (await self.get("https://snaptik.app/en")).text,
+                    )
+                ),
+            },
         )
-        if 'error_api_web;' in resp.text or 'Error:' in resp.text:
+        if "error_api_web;" in resp.text or "Error:" in resp.text:
             raise InvalidUrl()
         stderr.flush()
-        dec = decoder(*literal_eval(
-            findall(
-                r'\(\".*?,.*?,.*?,.*?,.*?.*?\)',
-                resp.text
-            )[0]
-        ))
+        dec = decoder(
+            *literal_eval(findall(r"\(\".*?,.*?,.*?,.*?,.*?.*?\)", resp.text)[0])
+        )
 
         stderr.flush()
         return [
-            DownloadAsync(
-                i,
-                self
+            DownloadAsync(i, self)
+            for i in set(
+                [
+                    "https://snaptik.app" + x.strip("\\")
+                    for x in findall(r"(/file.php?.*?)\"", dec)
+                ]
+                + [i.strip("\\") for i in findall(r"\"(https?://snapxcdn.*?)\"", dec)]
             )
-            for i in set(['https://snaptik.app' + x.strip('\\') for x in findall(
-                r'(/file.php?.*?)\"',
-                dec
-            )] + [i.strip('\\') for i in findall(
-                r'\"(https?://snapxcdn.*?)\"',
-                dec
-            )])
         ]
 
     async def __aiter__(self):