ccfx 0.9.0__tar.gz → 1.0.0__tar.gz

{ccfx-0.9.0/ccfx.egg-info → ccfx-1.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ccfx
-Version: 0.9.0
+Version: 1.0.0
 Summary: This package simplifies regular common actions for quick prototyping in a user friendly way
 Author-email: Celray James CHAWANDA <celray@chawanda.com>
 License-Expression: MIT

{ccfx-0.9.0 → ccfx-1.0.0}/ccfx/ccfx.py

@@ -14,7 +14,7 @@ import os, sys
 import glob
 import warnings
 from netCDF4 import Dataset
-from osgeo import gdal, osr
+from osgeo import gdal, ogr, osr
 import numpy
 from genericpath import exists
 import shutil
@@ -23,7 +23,6 @@ import pickle
 import time
 from shapely.geometry import box, Point
 import geopandas, pandas
-from osgeo import gdal, ogr, osr
 import py7zr
 import subprocess
 import multiprocessing
@@ -133,7 +132,7 @@ def guessMimeType(imagePath):
     return 'image/png'
 
 
-def downloadYoutubeVideo(url: str, dstDir: str, audioOnly: bool = False, dstFileName: Optional[str] = None ) -> str:
+def downloadYoutubeVideo(url: str, dstDir: str, audioOnly: bool = False, cookiesFile: str = None, dstFileName: Optional[str] = None ) -> str:
     """
     Download from YouTube via yt-dlp.
 
@@ -154,6 +153,9 @@ def downloadYoutubeVideo(url: str, dstDir: str, audioOnly: bool = False, dstFile
 
     opts = {"outtmpl": template}
 
+    if cookiesFile:
+        opts["cookiefile"] = cookiesFile
+
     if audioOnly:
         opts.update({
             "format": "bestaudio/best",
@@ -163,6 +165,7 @@ def downloadYoutubeVideo(url: str, dstDir: str, audioOnly: bool = False, dstFile
                 "preferredquality": "192",
             }],
         })
+        
     else:
         # prefer a single MP4 file (progressive), fallback to any best if none
         opts["format"] = "bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best"
@@ -181,6 +184,58 @@ def downloadYoutubeVideo(url: str, dstDir: str, audioOnly: bool = False, dstFile
     return os.path.join(dstDir, final)
 
 
+def parseYoutubePlaylist(playlistUrl: str) -> list[str]:
+    """
+    Return a list of full video URLs contained in a YouTube playlist.
+
+    Args:
+        playlistUrl: Full URL of the playlist (the one with &list=… or /playlist?list=…).
+
+    Returns:
+        List of video URLs in the order reported by YouTube.
+    """
+    opts = {
+        "quiet": True,
+        "extract_flat": "in_playlist",   # don’t recurse into each video
+    }
+
+    with yt_dlp.YoutubeDL(opts) as ytdl:
+        info = ytdl.extract_info(playlistUrl, download=False)
+
+    entries = info.get("entries", [])
+    return [f"https://www.youtube.com/watch?v={e['id']}" for e in entries if e.get("id")]
+
+
+def parseYoutubeChannelVideos(channelUrl: str, maxItems: Optional[int] = None) -> list[str]:
+    """
+    Return a list of video URLs published on a channel.
+
+    Args:
+        channelUrl: Any canonical channel URL, e.g.
+                    - https://www.youtube.com/@LinusTechTips
+                    - https://www.youtube.com/channel/UCXuqSBlHAE6Xw-yeJA0Tunw
+                    - https://www.youtube.com/c/NASA/videos
+        maxItems:   Optional hard limit. If None, returns every video the API exposes.
+
+    Returns:
+        List of video URLs, newest-first (YouTube’s default order).
+    """
+    opts = {
+        "quiet": True,
+        "extract_flat": True,      # treat the channel as one big “playlist”
+        "skip_download": True,
+    }
+
+    with yt_dlp.YoutubeDL(opts) as ytdl:
+        info = ytdl.extract_info(channelUrl, download=False)
+
+    entries = info.get("entries", [])
+    if maxItems is not None:
+        entries = entries[:maxItems]
+
+    return [f"https://www.youtube.com/watch?v={e['id']}" for e in entries if e.get("id")]
+
+
 def setMp3Metadata(fn, metadata, imagePath=None):
     '''
     This function takes a path to an mp3 and a metadata dictionary,
@@ -276,6 +331,39 @@ def deleteFile(filePath:str, v:bool = False) -> bool:
     
     return deleted
 
+
+def alert(message:str, server:str = "http://ntfy.sh", topic:str = "pythonAlerts", attachment:str = None, messageTitle:str = "info", priority:int = None, tags:list = [],  printIt:bool = True, v:bool = False) -> bool:
+    '''
+    This sends an alert to a given server in case you want to be notified of something
+    message         : the message to send
+    server          : the server to send the message to (default is http://ntfy.sh)
+    topic           : the topic to send the message to (default is pythonAlerts)
+    attachment      : a file to attach to the message (optional)
+    messageTitle    : the title of the message (optional, default is info)
+    priority        : the priority of the message (optional, default is None)
+    tags            : a list of tags to add to the message (optional, default is empty list)
+    printIt         : whether to print the message to the console (default is True)
+    v               : verbose (default is False, set to True to print debug info)
+
+    return: True if the alert was sent successfully, False otherwise
+    '''
+    print(message) if printIt else None; header_data = {}
+    if not messageTitle is None: header_data["Title"] = messageTitle
+    if not priority is None: header_data["Priority"] = priority
+    if not len(tags) == 0: header_data["Tags"] = ",".join(tags)
+
+    try:
+        if v: print(f"sending alert to {server}/{topic}")
+        if not attachment is None:
+            header_data["Filename"] = getFileBaseName(attachment)
+            requests.put( f"{server}/{topic}", data=open(attachment, 'rb'), headers=header_data )
+            return True
+        try: requests.post(f"{server}/{topic}",data=message, headers=header_data )
+        except: return False
+    except: return False
+    return True
+
+
 def deletePath(path:str, v:bool = False) -> bool:
     '''
     Delete a directory
@@ -309,6 +397,38 @@ def downloadChunk(url, start, end, path):
             if chunk:
                 f.write(chunk)
 
+
+def formatStringBlock(input_str, max_chars=70):
+    '''
+    This function takes a string and formats it into a block of text
+    with a maximum number of characters per line.
+
+    input_str: the string to format
+    max_chars: the maximum number of characters per line (default is 70)
+
+    '''
+    words = input_str.split(' ')
+    lines = []
+    current_line = ""
+
+    for word in words:
+        # If adding the next word to the current line would exceed the max_chars limit
+        if len(current_line) + len(word) > max_chars:
+            # Append current line to lines and start a new one
+            lines.append(current_line.strip())
+            current_line = word
+        else:
+            # Add the word to the current line
+            current_line += " " + word
+
+    # Append any remaining words
+    lines.append(current_line.strip())
+
+    return '\n'.join(lines)
+
+
+
+
 def downloadFile(url, save_path, exists_action='resume', num_connections=5, v=False):
     if v:
         print(f"\ndownloading {url}")
@@ -643,21 +763,45 @@ def renameNetCDFvariable(input_file: str, output_file: str, old_var_name: str, n
     except subprocess.CalledProcessError as e:
         print(f"Error: {e.stderr}")
 
-def compressTo7z(input_dir: str, output_file: str):
+
+def compressTo7z(input_dir: str, output_file: str, compressionLevel: int = 4, excludeExt: list = None, v: bool = False) -> None:
     """
     Compresses the contents of a directory to a .7z archive with maximum compression.
     
     :param input_dir: Path to the directory to compress
     :param output_file: Output .7z file path
+    :param compressionLevel: Compression level (0-9), default is 4 (maximum compression)
+    :param excludeExt: List of file extensions to exclude from compression
     """
+    if excludeExt is None:
+        excludeExt = []
+
     # Create the .7z archive with LZMA2 compression
-    with py7zr.SevenZipFile(output_file, 'w', filters=[{'id': py7zr.FILTER_LZMA2, 'preset': 9}]) as archive:
+    with py7zr.SevenZipFile(output_file, 'w', filters=[{'id': py7zr.FILTER_LZMA2, 'preset': compressionLevel}]) as archive:
         # Add each item in the input directory, avoiding the top-level folder in the archive
         for root, _, files in os.walk(input_dir):
             for file in files:
                 file_path = os.path.join(root, file)
+                
+                # Skip excluded file extensions
+                if any(file.endswith(ext) for ext in excludeExt):
+                    continue
                 # Add file to the archive with a relative path to avoid including the 'tmp' folder itself
                 archive.write(file_path, arcname=os.path.relpath(file_path, start=input_dir))
+    if v:
+        print(f"compressed {input_dir} to {output_file} with compression level {compressionLevel}.")
+
+
+def uncompress(inputFile: str, outputDir: str, v: bool = False) -> None:
+    """
+    Extracts an archive supported by py7zr (.7z, .zip, .tar, .tar.gz, .tar.bz2, .xz, .tar.xz) to outputDir.
+    inputFile: Path to the input archive file
+    outputDir: Directory where the contents will be extracted
+    v: Verbose flag to print extraction status (default is False)
+    """
+    if not exists(outputDir): createPath(outputDir)
+    with py7zr.SevenZipFile(inputFile, 'r') as archive: archive.extractall(path=outputDir)
+    if v: print(f"extracted {inputFile} to {outputDir}.")
 
 
 def moveDirectory(srcDir:str, destDir:str, v:bool = False) -> bool:
@@ -744,6 +888,21 @@ def clipRasterByExtent(inFile: str, outFile: str, bounds: tuple) -> str:
     ds = None
     return outFile
 
+
+def clipRasterByVector(inFile: str, outFile: str, vectorFile: str) -> str:
+    '''
+    Clips a raster using GDAL warp with a vector file
+    inFile: input raster path
+    outFile: output path
+    vectorFile: vector file path (e.g., shapefile or GeoJSON)
+    return: output path
+    '''
+    ds = gdal.Open(inFile)
+    gdal.Warp(outFile, ds, cutlineDSName=vectorFile, cropToCutline=True)
+    ds = None
+    return outFile
+
+
 def clipVectorByExtent(inFile: str, outFile: str, bounds: tuple) -> str:
     '''
     Clips a vector using GeoPandas

{ccfx-0.9.0 → ccfx-1.0.0/ccfx.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ccfx
-Version: 0.9.0
+Version: 1.0.0
 Summary: This package simplifies regular common actions for quick prototyping in a user friendly way
 Author-email: Celray James CHAWANDA <celray@chawanda.com>
 License-Expression: MIT

{ccfx-0.9.0 → ccfx-1.0.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ccfx"
-version = "0.9.0"
+version = "1.0.0"
 description = "This package simplifies regular common actions for quick prototyping in a user friendly way"
 readme = "README.md"
 license = "MIT"