tes fix kuso extract

misskaty/helper/kuso_utils.py

@@ -8,111 +8,56 @@ from telegraph.aio import Telegraph
 
 from misskaty import BOT_USERNAME
 from misskaty.helper.http import fetch
+from misskaty.helper.media_helper import post_to_telegraph
 
 LOGGER = logging.getLogger("MissKaty")
 
-headers = {
-    "Accept": "*/*",
-    "User-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.19582",
-}
 
-
+async def kusonimeBypass(url: str):
-async def kusonimeBypass(url: str, slug=None):
     result = {}
-    _url = url
+    page = await fetch.get(url)
-    if slug:
+    if page.status_code != 200:
-        noslug_url = "https://kusonime.com/{slug}"
+        raise Exception(f"ERROR: Hostname might be blocked by server!")
-        _url = noslug_url.format({"slug": slug})
     try:
-        page = await fetch.get(_url, headers=headers)
         soup = BeautifulSoup(page.text, "lxml")
         thumb = soup.find("div", {"class": "post-thumb"}).find("img").get("src")
         data = []
+        # title = soup.select("#venkonten > div.vezone > div.venser > div.venutama > div.lexot > p:nth-child(3) > strong")[0].text.strip()
         try:
             title = soup.find("h1", {"class": "jdlz"}).text  # fix title njing haha
-            season = (
+            season = soup.select("#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(3)")[0].text.split(":").pop().strip()
-                soup.select(
+            tipe = soup.select("#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(5)")[0].text.split(":").pop().strip()
-                    "#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(3)"
+            status_anime = soup.select("#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(6)")[0].text.split(":").pop().strip()
-                )[0]
+            ep = soup.select("#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(7)")[0].text.split(":").pop().strip()
-                .text.split(":")
+            score = soup.select("#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(8)")[0].text.split(":").pop().strip()
-                .pop()
+            duration = soup.select("#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(9)")[0].text.split(":").pop().strip()
-                .strip()
+            rilis = soup.select("#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(10)")[0].text.split(":").pop().strip()
-            )
-            tipe = (
-                soup.select(
-                    "#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(5)"
-                )[0]
-                .text.split(":")
-                .pop()
-                .strip()
-            )
-            status_anime = (
-                soup.select(
-                    "#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(6)"
-                )[0]
-                .text.split(":")
-                .pop()
-                .strip()
-            )
-            ep = (
-                soup.select(
-                    "#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(7)"
-                )[0]
-                .text.split(":")
-                .pop()
-                .strip()
-            )
-            score = (
-                soup.select(
-                    "#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(8)"
-                )[0]
-                .text.split(":")
-                .pop()
-                .strip()
-            )
-            duration = (
-                soup.select(
-                    "#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(9)"
-                )[0]
-                .text.split(":")
-                .pop()
-                .strip()
-            )
-            rilis = (
-                soup.select(
-                    "#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(10)"
-                )[0]
-                .text.split(":")
-                .pop()
-                .strip()
-            )
         except Exception:
             e = traceback.format_exc()
             LOGGER.error(e)
-            title, season, tipe, status_anime, ep, score, duration, rilis = (
+            title, season, tipe, status_anime, ep, score, duration, rilis = "None", "None", "None", "None", 0, 0, 0, "None"
-                "None",
+        num = 1
-                "None",
-                "None",
-                "None",
-                0,
-                0,
-                0,
-                "None",
-            )
         genre = []
-        for _genre in soup.select(
+        for _genre in soup.select("#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(2)"):
-            "#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(2)"
-        ):
             gen = _genre.text.split(":").pop().strip().split(", ")
             genre = gen
-        for _, smokedl in enumerate(
+        for smokedl in soup.find("div", {"class": "dlbodz"}).find_all("div", {"class": "smokeddlrh"}):
-            soup.find("div", {"class": "dlbodz"}).find_all(
+            if not smokedl:
-                "div", {"class": "smokeddlrh"}
+                continue
-            ),
-            start=1,
-        ):
             mendata = {"name": title, "links": []}
+            for smokeurl in smokedl.find_all("div", {"class": "smokeurl"}):
+                if not smokeurl:
+                    continue
+                quality = smokeurl.find("strong").text
+                links = []
+                for link in smokeurl.find_all("a"):
+                    url = link.get("href")
+                    client = link.text
+                    links.append({"client": client, "url": url})
+                mendata["links"].append({"quality": quality, "link_download": links})
             for smokeurl in smokedl.find_all("div", {"class": "smokeurlrh"}):
+                if not smokeurl:
+                    continue
                 quality = smokeurl.find("strong").text
                 links = []
                 for link in smokeurl.find_all("a"):
@@ -121,45 +66,62 @@ async def kusonimeBypass(url: str, slug=None):
                     links.append({"client": client, "url": url})
                 mendata["links"].append({"quality": quality, "link_download": links})
             data.append(mendata)
-        result |= {
+            num += 1
-            "error": False,
+        for smokedl in soup.find("div", {"class": "dlbodz"}).find_all("div", {"class": "smokeddl"}):
-            "title": title,
+            if not smokedl:
-            "thumb": thumb,
+                continue
-            "genre": genre,
+            mendata = {"name": title, "links": []}
-            "genre_string": ", ".join(genre),
+            for smokeurl in smokedl.find_all("div", {"class": "smokeurl"}):
-            "status_anime": status_anime,
+                if not smokeurl:
-            "season": season,
+                    continue
-            "tipe": tipe,
+                quality = smokeurl.find("strong").text
-            "ep": ep,
+                links = []
-            "score": score,
+                for link in smokeurl.find_all("a"):
-            "duration": duration,
+                    url = link.get("href")
-            "rilis": rilis,
+                    client = link.text
-            "data": data,
+                    links.append({"client": client, "url": url})
-        }
+                mendata["links"].append({"quality": quality, "link_download": links})
-    except Exception:
+            for smokeurl in smokedl.find_all("div", {"class": "smokeurlrh"}):
+                if not smokeurl:
+                    continue
+                quality = smokeurl.find("strong").text
+                links = []
+                for link in smokeurl.find_all("a"):
+                    url = link.get("href")
+                    client = link.text
+                    links.append({"client": client, "url": url})
+                mendata["links"].append({"quality": quality, "link_download": links})
+            data.append(mendata)
+            num += 1
+        result.update({"title": title, "thumb": thumb, "genre": genre, "genre_string": ", ".join(genre), "status_anime": status_anime, "season": season, "tipe": tipe, "ep": ep, "score": score, "duration": duration, "rilis": rilis, "data": data})
+    except Exception as e:
+        if len(result) != 0:
+            result.clear()
         err = traceback.format_exc()
-        LOGGER.error(err)
+        page.close()
-        result |= {"error": True, "error_message": err}
+        LOGGER.error(f"class: {e.__class__.__name_}, {err}")
-    await http.delete(_url)
+        raise Exception(f"ERROR: {err}")
-    return result
+    finally:
+        page.close()
+        return result
 
 
-async def byPassPh(url: str, name: str):
+async def byPassPh(url: str, name: str) -> Optional[str]:
     kusonime = await kusonimeBypass(url)
-    results = {"error": True, "error_message": kusonime}
+    if not isinstance(kusonime, dict):
-    if not kusonime["error"]:
+        return kusonime
-        template = """
+    template = """
 <img src={{{thumb}}}>
 
 <p><b>Title</b> : <code>{{title}}</code></p>
 <p><b>Genre</b> : <code>{{genre_string}}</code></p>
-<br><br><p><b>Season</b> : <code>{{season}}</code></p>
+<br><p><b>Season</b> : <code>{{season}}</code></p>
-<br><br><p><b>Type</b> : <code>{{tipe}}</code></p>
+<br><p><b>Type</b> : <code>{{tipe}}</code></p>
-<br><br><p><b>Status</b> : <code>{{status_anime}}</code></p>
+<br><p><b>Status</b> : <code>{{status_anime}}</code></p>
-<br><br><p><b>Total Episode</b> : <code>{{ep}}</code></p>
+<br><p><b>Total Episode</b> : <code>{{ep}}</code></p>
-<br><br><p><b>Score</b> : <code>{{score}}</code></p>
+<br><p><b>Score</b> : <code>{{score}}</code></p>
-<br><br><p><b>Duration</b> : <code>{{duration}}</code></p>
+<br><p><b>Duration</b> : <code>{{duration}}</code></p>
-<br><br><p><b>Released on</b> : <code>{{rilis}}</code></p>
+<br><p><b>Released on</b> : <code>{{rilis}}</code></p>
 <br><br>
 {{#data}}
     <h4>{{name}}</h4>
@@ -172,16 +134,10 @@ async def byPassPh(url: str, name: str):
     <br>
 {{/data}}
 """.strip()
-        html = chevron.render(template, kusonime)
+    plink = await post_to_telegraph(
-        telegraph = Telegraph()
+        False, f"{kusonime.get('title')} By {escape(name)}", render(template, kusonime))
-        if not telegraph.get_access_token():
+    )
-            await telegraph.create_account(short_name=BOT_USERNAME)
+    return "https://telegra.ph/{}".format(plink)
-        page = await telegraph.create_page(
-            f"{kusonime.get('title')} By {escape(name)}", html_content=html
-        )
-        results |= {"error": False, "url": f'https://telegra.ph/{page["path"]}'}
-        del results["error_message"]
-    return results
 
 
 class Kusonime:

misskaty/plugins/web_scraper.py

@@ -185,13 +185,12 @@ async def getDataPahe(msg, kueri, CurrentPage, strings):
 async def getDataKuso(msg, kueri, CurrentPage, user, strings):
     if not SCRAP_DICT.get(msg.id):
         kusodata = []
-        try:
+        data = await fetch.get(
-            data = await fetch.get(
+            f"{web['kusonime']}/?s={kueri}", follow_redirects=True
-                f"{web['kusonime']}/?s={kueri}", follow_redirects=True
+        )
-            )
+        if data.status_code != 200:
-        except Exception as err:
             await msg.edit_msg(strings("err_getweb").format(err=err))
-            return None, None
+            return None, 0, None, None
         res = BeautifulSoup(data, "lxml").find_all("h2", {"class": "episodeye"})
         for i in res:
             ress = i.find_all("a")[0]
@@ -238,11 +237,10 @@ async def getDataKuso(msg, kueri, CurrentPage, user, strings):
 async def getDataMovieku(msg, kueri, CurrentPage, strings):
     if not SCRAP_DICT.get(msg.id):
         moviekudata = []
-        try:
+        data = await fetch.get(
-            data = await fetch.get(
+            f"{web['movieku']}/?s={kueri}", follow_redirects=True
-                f"{web['movieku']}/?s={kueri}", follow_redirects=True
+        )
-            )
+        if data.status_code != 200:
-        except Exception as err:
             await msg.edit_msg(strings("err_getweb").format(err=err))
             return None, None
         r = BeautifulSoup(data, "lxml")
@@ -279,12 +277,10 @@ async def getDataMovieku(msg, kueri, CurrentPage, strings):
 async def getDataNodrakor(msg, kueri, CurrentPage, user, strings):
     if not SCRAP_DICT.get(msg.id):
         nodrakordata = []
-        try:
+        data = await fetch.get(
-            data = await fetch.get(
+            f"{web['nodrakor']}/?s={kueri}", follow_redirects=True,
-                f"{web['nodrakor']}/?s={kueri}",
+        )
-                follow_redirects=True,
+        if data.status_code != 200:
-            )
-        except Exception as err:
             await msg.edit_msg(strings("err_getweb").format(err=err))
             return None, 0, None
         text = BeautifulSoup(data, "lxml")
@@ -331,12 +327,10 @@ async def getDataNodrakor(msg, kueri, CurrentPage, user, strings):
 async def getDataSavefilm21(msg, kueri, CurrentPage, user, strings):
     if not SCRAP_DICT.get(msg.id):
         sfdata = []
-        try:
+        data = await fetch.get(
-            data = await fetch.get(
+            f"{web['savefilm21']}/?s={kueri}", follow_redirects=True,
-                f"{web['savefilm21']}/?s={kueri}",
+        )
-                follow_redirects=True,
+        if data.status_code != 200:
-            )
-        except Exception as err:
             await msg.edit_msg(strings("err_getweb").format(err=err))
             return None, 0, None
         text = BeautifulSoup(data, "lxml")
@@ -382,15 +376,13 @@ async def getDataSavefilm21(msg, kueri, CurrentPage, user, strings):
 # Lendrive GetData
 async def getDataLendrive(msg, kueri, CurrentPage, user, strings):
     if not SCRAP_DICT.get(msg.id):
-        try:
+        if kueri:
-            if kueri:
+            data = await fetch.get(
-                data = await fetch.get(
+                f"{web['lendrive']}/?s={kueri}", follow_redirects=True,
-                    f"{web['lendrive']}/?s={kueri}",
+            )
-                    follow_redirects=True,
+        else:
-                )
+            data = await fetch.get(web["lendrive"], follow_redirects=True)
-            else:
+        if data.status_code != 200:
-                data = await fetch.get(web["lendrive"], follow_redirects=True)
-        except Exception as err:
             await msg.edit_msg(strings("err_getweb").format(err=err))
             return None, 0, None
         res = BeautifulSoup(data, "lxml")
@@ -442,12 +434,10 @@ async def getDataLendrive(msg, kueri, CurrentPage, user, strings):
 # MelongMovie GetData
 async def getDataMelong(msg, kueri, CurrentPage, user, strings):
     if not SCRAP_DICT.get(msg.id):
-        try:
+        data = await fetch.get(
-            data = await fetch.get(
+            f"{web['melongmovie']}/?s={kueri}", follow_redirects=True,
-                f"{web['melongmovie']}/?s={kueri}",
+        )
-                follow_redirects=True,
+        if data.status_code != 200:
-            )
-        except Exception as err:
             await msg.edit_msg(strings("err_getweb").format(err=err))
             return None, 0, None
         bs4 = BeautifulSoup(data, "lxml")
@@ -492,13 +482,12 @@ async def getDataMelong(msg, kueri, CurrentPage, user, strings):
 # GoMov GetData
 async def getDataGomov(msg, kueri, CurrentPage, user, strings):
     if not SCRAP_DICT.get(msg.id):
-        try:
+        gomovv = await fetch.get(
-            gomovv = await fetch.get(
+            f"{web['gomov']}/?s={kueri}", follow_redirects=True
-                f"{web['gomov']}/?s={kueri}", follow_redirects=True
+        )
-            )
+        if gomovv.status_code != 200:
-        except Exception as err:
             await msg.edit_msg(strings("err_getweb").format(err=err))
-            return None, None
+            return None, 0, None
         text = BeautifulSoup(gomovv, "lxml")
         entry = text.find_all(class_="entry-header")
         if entry[0].text.strip() == "Nothing Found":
@@ -548,12 +537,11 @@ async def getDataGomov(msg, kueri, CurrentPage, user, strings):
 async def getSame(msg, query, current_page, strings):
     if not SCRAP_DICT.get(msg.id):
         cfse = cloudscraper.create_scraper()
-        try:
+        if query:
-            if query:
+            data = cfse.get(f"{web['samehadaku']}/?s={query}")
-                data = cfse.get(f"{web['samehadaku']}/?s={query}")
+        else:
-            else:
+            data = cfse.get(web["samehadaku"])
-                data = cfse.get(web["samehadaku"])
+        if data.status_code != 200:
-        except Exception as err:
             await msg.edit_msg(strings("err_getweb").format(err=err))
             return None, None
         res = BeautifulSoup(data.text, "lxml").find_all(class_="animposx")