merge all video parsers

app.py

@@ -1,113 +1,19 @@
-import os
-import re
-import shutil
-import requests
 import gradio as gr
-from datetime import datetime
-from zoneinfo import ZoneInfo
-from tzlocal import get_localzone
-
-TIMEOUT = None
-API = os.getenv("api_tiktok")
-
-
-def timestamp(naive_time: datetime = None, target_tz=ZoneInfo("Asia/Shanghai")):
-    if not naive_time:
-        naive_time = datetime.now()
-
-    local_tz = get_localzone()
-    aware_local = naive_time.replace(tzinfo=local_tz)
-    return aware_local.astimezone(target_tz).strftime("%Y-%m-%d %H:%M:%S")
-
-
-def download_file(url, video_id, cache_dir="./__pycache__"):
-    if os.path.exists(cache_dir):
-        shutil.rmtree(cache_dir)
-
-    os.makedirs(cache_dir)
-    local_file = f"{cache_dir}/{video_id}.mp4"
-    response = requests.get(url, stream=True)
-    if response.status_code == 200:
-        with open(local_file, "wb") as file:
-            for chunk in response.iter_content(chunk_size=8192):
-                file.write(chunk)
-
-    print(f"[{timestamp()}] File was downloaded to {local_file}")
-    return local_file
-
-
-def extract_fst_url(text):
-    url_pattern = r'(https?://[^\s"]+)'
-    match = re.search(url_pattern, text)
-    if match:
-        return match.group(1)
-    else:
-        return None
-
-
-def infer(video_url):
-    video = parse_time = desc = avatar = author = sign = None
-    if not video_url:
-        desc = "The video sharing link is empty!"
-        return video, desc, parse_time, avatar, author, sign
-
-    video_url = extract_fst_url(video_url)
-    if not video_url:
-        desc = "Please enter a valid video sharing link!"
-        return video, desc, parse_time, avatar, author, sign
-
-    try:
-        response = requests.get(API, params={"url": video_url}, timeout=TIMEOUT)
-        response_json = response.json()
-        retcode = response_json["code"]
-        if retcode == 200:
-            response_data = response_json["data"]
-            video_id = response_data["play_url"].split("video_id=")[1].split("&")[0]
-            video = download_file(response_data["video_url"], video_id)
-            parse_time = response_data["parse_time"]
-
-            additional_data = response_data["additional_data"][0]
-            desc = additional_data["desc"]
-            avatar = additional_data["url"].split("?from=")[0]
-            author = additional_data["nickname"]
-            sign = additional_data["signature"]
-
-        else:
-            desc = f"Interface call failed, error code: HTTP {retcode}"
-
-    except Exception as e:
-        desc = f"Video parsing failed: {e}"
-
-    return video, desc, parse_time, avatar, author, sign
-
+from tiktok import tiktok_parser
+from bili import bili_parser
+from bvid2acid import bv2acid
 
 if __name__ == "__main__":
-    gr.Interface(
-        fn=infer,
-        inputs=[
-            gr.Textbox(
-                label="Please enter TikTok video sharing short link",
-                placeholder="https://v.douyin.com/*",
-            ),
-        ],
-        outputs=[
-            gr.Video(
-                label="Video download",
-                show_download_button=True,
-                show_share_button=False,
-            ),
-            gr.Textbox(label="Video description", show_copy_button=True),
-            gr.Textbox(label="Parsing time", show_copy_button=True),
-            gr.Image(label="Author avatar", show_share_button=False),
-            gr.Textbox(label="Author nickname", show_copy_button=True),
-            gr.TextArea(label="Author signature", show_copy_button=True),
-        ],
-        title="Parse TikTok video without watermark",
-        description="This site does not provide any video storage services, only to provide the most basic resolution services",
-        flagging_mode="never",
-        examples=[
-            "https://v.douyin.com/8FVe5DzarE0",
-            "8.20 Njc:/ [email protected] 11/03 黑塔女士举世无双！# 大黑塔 # 黑塔 # 崩坏星穹铁道 # 再创世的凯歌 # 天才俱乐部  https://v.douyin.com/8FVe5DzarE0/ 复制此链接，打开Dou音搜索，直接观看视频！",
-        ],
-        cache_examples=False,
-    ).launch()
+    with gr.Blocks() as demo:
+        gr.Markdown(
+            "This site does not provide any video storage services, only to provide the most basic resolution services"
+        )
+        with gr.Tab("Tiktok"):
+            tiktok_parser()
+
+        with gr.Tab("Bilibili"):
+            with gr.Column():
+                bv2acid()
+                bili_parser()
+
+    demo.launch()

bili.py

@@ -0,0 +1,117 @@
+import os
+import re
+import shutil
+import requests
+import gradio as gr
+from utils import timestamp
+from config import TMP_DIR, HEADER, TIMEOUT, API_BILI
+
+
+def download_file(url, video_id, cache_dir=TMP_DIR):
+    if os.path.exists(cache_dir):
+        shutil.rmtree(cache_dir)
+
+    os.makedirs(cache_dir)
+    local_file = f"{cache_dir}/{video_id}.mp4"
+    response = requests.get(url, stream=True)
+    if response.status_code == 200:
+        with open(local_file, "wb") as file:
+            for chunk in response.iter_content(chunk_size=8192):
+                file.write(chunk)
+
+    print(f"[{timestamp()}] File was downloaded to {local_file}")
+    return local_file
+
+
+def extract_fst_url(text):
+    url_pattern = r'(https?://[^\s"]+)'
+    match = re.search(url_pattern, text)
+    if match:
+        out_url = match.group(1).split("?")[0]
+        if out_url[-1] == "/":
+            out_url = out_url[:-1]
+
+        return out_url
+
+    else:
+        return f"https://www.bilibili.com/video/{text}"
+
+
+def get_real_url(short_url):
+    return requests.get(
+        short_url,
+        headers=HEADER,
+        allow_redirects=True,
+        timeout=TIMEOUT,
+    ).url.split("/?")[0]
+
+
+def infer(video_url: str, p: int):
+    title = cover = desc = dur = video = author = avatar = None
+    if not video_url:
+        title = "Empty video link!"
+        return title, cover, video, desc, dur, avatar, author
+
+    video_url = extract_fst_url(video_url)
+    try:
+        if "b23.tv" in video_url:
+            video_url = get_real_url(video_url)
+
+        response = requests.get(API_BILI, params={"url": video_url}, timeout=TIMEOUT)
+        response_json = response.json()
+        retcode = response_json["code"]
+        if retcode == 1:
+            title = response_json["title"]
+            cover = response_json["imgurl"]
+            desc = response_json["desc"]
+
+            response_data = response_json["data"][int(p) - 1]
+            dur = response_data["duration"]
+            video_id = video_url.split("/")[-1]
+            video = download_file(response_data["video_url"], video_id)
+
+            author_data = response_json["user"]
+            author = author_data["name"]
+            avatar = author_data["user_img"]
+
+        else:
+            title = f"Failed to call API, error code: {retcode}"
+
+    except Exception as e:
+        title = f"Failed to parse video: {e}"
+
+    return title, cover, video, desc, dur, avatar, author
+
+
+def bili_parser():
+    return gr.Interface(
+        fn=infer,
+        inputs=[
+            gr.Textbox(
+                label="Please input Bilibili video link",
+                placeholder="https://www.bilibili.com/video/*",
+            ),
+            gr.Slider(label="Part", minimum=1, maximum=1000, step=1, value=1),
+        ],
+        outputs=[
+            gr.Textbox(label="Video title", show_copy_button=True),
+            gr.Image(label="Video cover", show_share_button=False),
+            gr.Video(
+                label="Download video",
+                show_download_button=True,
+                show_share_button=False,
+            ),
+            gr.TextArea(label="Video introduction", show_copy_button=True),
+            gr.Textbox(label="Video duration(s)", show_copy_button=True),
+            gr.Image(label="Uploader avatar", show_share_button=False),
+            gr.Textbox(label="Uploader nickname", show_copy_button=True),
+        ],
+        title="Bilibili video parser",
+        flagging_mode="never",
+        examples=[
+            ["BV1G8iRYBE4f", 1],
+            ["https://b23.tv/LSoJzpW", 1],
+            ["https://www.bilibili.com/video/BV1G8iRYBE4f", 1],
+        ],
+        cache_examples=False,
+    )

bvid2acid.py

@@ -0,0 +1,31 @@
+import requests
+import gradio as gr
+
+
+def infer(bvid: str):
+    try:
+        response = requests.get(
+            "https://api.bilibili.com/x/web-interface/view",
+            params={"bvid": bvid},
+            headers={
+                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36 Edg/131.0.0.0"
+            },
+        )
+        data = response.json()["data"]
+        return data["aid"], data["cid"]
+
+    except Exception as e:
+        return "Failed to parse aid / cid", f"{e}"
+
+
+def bv2acid():
+    return gr.Interface(
+        fn=infer,
+        inputs=gr.Textbox(label="bvid", show_copy_button=True),
+        outputs=[
+            gr.Textbox(label="aid", show_copy_button=True),
+            gr.Textbox(label="cid", show_copy_button=True),
+        ],
+        title="Bvid to aid / cid",
+        flagging_mode="never",
+    )

config.py

@@ -0,0 +1,11 @@
+import os
+
+TIMEOUT = None
+TMP_DIR = "./__pycache__"
+
+API_BILI = os.getenv("api_bili")
+API_TIKTOK = os.getenv("api_tiktok")
+
+HEADER = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.116 Safari/537.36"
+}

tiktok.py

@@ -0,0 +1,99 @@
+import os
+import re
+import shutil
+import requests
+import gradio as gr
+from utils import timestamp
+from config import API_TIKTOK, TIMEOUT, TMP_DIR
+
+
+def download_file(url, video_id, cache_dir=TMP_DIR):
+    if os.path.exists(cache_dir):
+        shutil.rmtree(cache_dir)
+
+    os.makedirs(cache_dir)
+    local_file = f"{cache_dir}/{video_id}.mp4"
+    response = requests.get(url, stream=True)
+    if response.status_code == 200:
+        with open(local_file, "wb") as file:
+            for chunk in response.iter_content(chunk_size=8192):
+                file.write(chunk)
+
+    print(f"[{timestamp()}] File was downloaded to {local_file}")
+    return local_file
+
+
+def extract_fst_url(text):
+    url_pattern = r'(https?://[^\s"]+)'
+    match = re.search(url_pattern, text)
+    if match:
+        return match.group(1)
+    else:
+        return None
+
+
+def infer(video_url):
+    video = parse_time = desc = avatar = author = sign = None
+    if not video_url:
+        desc = "The video sharing link is empty!"
+        return video, desc, parse_time, avatar, author, sign
+
+    video_url = extract_fst_url(video_url)
+    if not video_url:
+        desc = "Please enter a valid video sharing link!"
+        return video, desc, parse_time, avatar, author, sign
+
+    try:
+        response = requests.get(API_TIKTOK, params={"url": video_url}, timeout=TIMEOUT)
+        response_json = response.json()
+        retcode = response_json["code"]
+        if retcode == 200:
+            response_data = response_json["data"]
+            video_id = response_data["play_url"].split("video_id=")[1].split("&")[0]
+            video = download_file(response_data["video_url"], video_id)
+            parse_time = response_data["parse_time"]
+
+            additional_data = response_data["additional_data"][0]
+            desc = additional_data["desc"]
+            avatar = additional_data["url"].split("?from=")[0]
+            author = additional_data["nickname"]
+            sign = additional_data["signature"]
+
+        else:
+            desc = f"Interface call failed, error code: HTTP {retcode}"
+
+    except Exception as e:
+        desc = f"Video parsing failed: {e}"
+
+    return video, desc, parse_time, avatar, author, sign
+
+
+def tiktok_parser():
+    return gr.Interface(
+        fn=infer,
+        inputs=[
+            gr.Textbox(
+                label="Please enter TikTok video sharing short link",
+                placeholder="https://v.douyin.com/*",
+            ),
+        ],
+        outputs=[
+            gr.Video(
+                label="Video download",
+                show_download_button=True,
+                show_share_button=False,
+            ),
+            gr.Textbox(label="Video description", show_copy_button=True),
+            gr.Textbox(label="Parsing time", show_copy_button=True),
+            gr.Image(label="Author avatar", show_share_button=False),
+            gr.Textbox(label="Author nickname", show_copy_button=True),
+            gr.TextArea(label="Author signature", show_copy_button=True),
+        ],
+        title="Parse TikTok video without watermark",
+        flagging_mode="never",
+        examples=[
+            "https://v.douyin.com/8FVe5DzarE0",
+            "8.20 Njc:/ [email protected] 11/03 黑塔女士举世无双！# 大黑塔 # 黑塔 # 崩坏星穹铁道 # 再创世的凯歌 # 天才俱乐部  https://v.douyin.com/8FVe5DzarE0/ 复制此链接，打开Dou音搜索，直接观看视频！",
+        ],
+        cache_examples=False,
+    )

utils.py

@@ -0,0 +1,12 @@
+from datetime import datetime
+from zoneinfo import ZoneInfo
+from tzlocal import get_localzone
+
+
+def timestamp(naive_time: datetime = None, target_tz=ZoneInfo("Asia/Shanghai")):
+    if not naive_time:
+        naive_time = datetime.now()
+
+    local_tz = get_localzone()
+    aware_local = naive_time.replace(tzinfo=local_tz)
+    return aware_local.astimezone(target_tz).strftime("%Y-%m-%d %H:%M:%S")