py-youtube-search 0.2.1__py3-none-any.whl

py_youtube_search/__init__.py

@@ -0,0 +1,85 @@
+import re
+import aiohttp
+import asyncio
+
+# Filter constants accessible to the user
+class Filters:
+    # Duration: 3 - 20 Minutes (Medium)
+    medium_today = "EgYIAhABGAU="
+    medium_this_week = "EgQIAxGF"
+    medium_this_month = "EgYIBBABGAU="
+    medium_this_year = "EgYIBRABGAU="
+
+    # Duration: Over 20 Minutes (Long)
+    long_today = "EgYIAhABGAI="
+    long_this_week = "EgQIAxAB"
+    long_this_month = "EgYIBBABGAI="
+    long_this_year = "EgYIBRABGAI="
+
+class YouTubeSearch:
+    def __init__(self, keywords: str, sp: str = None, limit: int = 15):
+        """
+        Initialize the search parameters.
+        Note: No network request happens here. Call .search() to fetch data.
+        """
+        self.keywords = keywords.replace(" ", "+")
+        self.sp = sp
+        self.limit = limit
+        self.source = None
+        self.base_url = "https://www.youtube.com/results"
+
+    async def _fetch_source(self):
+        params = {"search_query": self.keywords}
+        if self.sp:
+            params["sp"] = self.sp
+
+        headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
+        }
+
+        async with aiohttp.ClientSession() as session:
+            async with session.get(self.base_url, params=params, headers=headers) as response:
+                return await response.text()
+
+    async def search(self):
+        """
+        Asynchronously fetches and parses the search results.
+        Returns a list of videos.
+        """
+        if not self.source:
+            self.source = await self._fetch_source()
+
+        # Regex to capture distinct JSON fields for ID, Title, Duration, and Views.
+        pattern = (
+            r'\"videoRenderer\":\{'
+            r'.+?\"videoId\":\"(?P<id>\S{11})\"'
+            r'.+?\"title\":\{\"runs\":\[\{\"text\":\"(?P<title>.+?)\"\}\]'
+            r'.+?\"lengthText\":\{.*?\"simpleText\":\"(?P<duration>.+?)\"\}'
+            r'.+?\"viewCountText\":\{\"simpleText\":\"(?P<views>.+?)\"\}'
+        )
+
+        matches = re.finditer(pattern, self.source)
+        
+        results = []
+        for match in matches:
+            if len(results) >= self.limit:
+                break
+            
+            data = match.groupdict()
+            results.append({
+                "id": data["id"],
+                "title": data["title"],
+                "duration": data["duration"],
+                "views": data["views"],
+                "url_suffix": f"/watch?v={data['id']}"
+            })
+
+        return results
+
+# --- Usage Example (Async) ---
+# import asyncio
+# async def main():
+#     yt = YouTubeSearch("LangGraph", sp=Filters.long_this_week)
+#     videos = await yt.search()
+#     print(videos)
+# asyncio.run(main())

py_youtube_search-0.2.1.dist-info/METADATA

@@ -0,0 +1,127 @@
+Metadata-Version: 2.4
+Name: py-youtube-search
+Version: 0.2.1
+Summary: A lightweight, regex-based YouTube search library without API keys.
+Home-page: https://github.com/VishvaRam/py-youtube-search
+Author: VishvaRam
+Author-email: murthyvishva@gmail.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-python
+Dynamic: summary
+
+
+# py-youtube-search
+
+A lightweight, asynchronous Python library to search YouTube videos programmatically without an API key. 
+It scrapes search results using `aiohttp` and `re`, making it fast, robust, and perfect for high-performance applications.
+
+## Features
+
+- **Async Support**: Fully asynchronous using `aiohttp` for non-blocking execution.
+- **No API Key Required**: Search YouTube directly without setting up Google Cloud projects.
+- **Advanced Filtering**: Built-in support for duration (Medium 3-20m, Long >20m) and upload date filters.
+- **Rich Data Extraction**: Extracts Video ID, Title, Duration, and View Count using optimized regex.
+
+## Installation
+
+```bash
+pip install py-youtube-search
+```
+
+## Quick Start
+
+### 1. Basic Async Search
+Fetch the top results for any keyword asynchronously.
+
+```python
+import asyncio
+from py_youtube_search import YouTubeSearch
+
+async def main():
+    # 1. Initialize the search (no network call yet)
+    yt = YouTubeSearch("Python async tutorials", limit=5)
+    
+    # 2. Await the search results
+    videos = await yt.search()
+
+    for v in videos:
+        print(f"Title: {v['title']}")
+        print(f"Duration: {v['duration']}")
+        print(f"Views: {v['views']}")
+        print(f"Link: https://www.youtube.com/watch?v={v['id']}\n")
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+### 2. Advanced Search with Filters
+Search for specific content, like long-form videos (>20m) uploaded this week.
+
+```python
+import asyncio
+from py_youtube_search import YouTubeSearch, Filters
+
+async def main():
+    # Use the Filters class for readable constants
+    yt = YouTubeSearch("LangGraph", sp=Filters.long_this_week, limit=3)
+    
+    videos = await yt.search()
+
+    for v in videos:
+        print(f"🎥 {v['title']} | ⏱ {v['duration']} | 👁 {v['views']}")
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+## Available Filters
+
+Pass these constants into the `sp` parameter of `YouTubeSearch`.
+
+### Duration: Medium (3 - 20 Minutes)
+| Filter Attribute | Description |
+| :--- | :--- |
+| `Filters.medium_today` | Uploaded **Today** |
+| `Filters.medium_this_week` | Uploaded **This Week** |
+| `Filters.medium_this_month` | Uploaded **This Month** |
+| `Filters.medium_this_year` | Uploaded **This Year** |
+
+### Duration: Long (Over 20 Minutes)
+| Filter Attribute | Description |
+| :--- | :--- |
+| `Filters.long_today` | Uploaded **Today** |
+| `Filters.long_this_week` | Uploaded **This Week** |
+| `Filters.long_this_month` | Uploaded **This Month** |
+| `Filters.long_this_year` | Uploaded **This Year** |
+
+## Data Structure
+
+The `.search()` method returns a list of dictionaries:
+
+```json
+[
+  {
+    "id": "lDoYisPfcck",
+    "title": "Hack the planet! LangGraph AI HackBot Dev & Q/A",
+    "duration": "1:05:23",
+    "views": "1.2K views",
+    "url_suffix": "/watch?v=lDoYisPfcck"
+  }
+]
+```
+
+## Dependencies
+- `aiohttp` (for async requests)
+
+## License
+MIT License. See LICENSE file for details.

py_youtube_search-0.2.1.dist-info/RECORD

@@ -0,0 +1,5 @@
+py_youtube_search/__init__.py,sha256=hWJcqytPfRODGIFynNmDrCQm_9P5zWwg4DOcWIyrVog,2769
+py_youtube_search-0.2.1.dist-info/METADATA,sha256=mr7bxYgCXk7VOF3pe5DNyen4CSg4Kha1CUFppENZwOc,3591
+py_youtube_search-0.2.1.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+py_youtube_search-0.2.1.dist-info/top_level.txt,sha256=4EMqIznKjzwgAcB_78SKaMIzZXpIxWQ4SRLeakY3fzQ,18
+py_youtube_search-0.2.1.dist-info/RECORD,,

py_youtube_search-0.2.1.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.10.2)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

py_youtube_search-0.2.1.dist-info/top_level.txt

@@ -0,0 +1 @@
+py_youtube_search