Downloading Files from URLs and zip downloaded files in python

Question

I am trying to write a script that helps me to download files from URLs. after downloading all the files I will zip them.

right now I can download files from URLs that have a filename in the URL for instance https://omextemplates.content.office.net/support/templates/en-us/tf16402488.dotx

my code works like this.

first: I am creating a folder with a unique name.I am getting the folder name from the caller function

def createFolder(folder_name,parent_dir):
    directory = folder_name
    path = os.path.join(parent_dir , str(directory))

    try :
        os.mkdir(path)
        return path
    except OSError as error :
        print(error)
    

    return None

Second: I will download all the files into this folder. I am getting the folder path from the caller. the folder path just created by above function

def download_file(url, folder_path, filename_to_be_download=''):

    req = requests.get(url, stream = True)
    try:
        if filename_to_be_download == "":
            return None
        else:
            filename = req.url[downloadUrl.rfind('/')+1:]

            file_path = os.path.join(folder_path, filename_to_be_download)
            with requests.get(url) as req:
                with open(file_path, 'wb') as f:
                    for chunk in req.iter_content(chunk_size=2024):
                        if chunk:
                            f.write(chunk)
                return file_path
    except Exception as e:
        # print(e)
        return None

third: I loop over all the download files present inside the folder with unique name in order to create a zip of them

def run():
    # for local
    parent_dir = "D:/A/scrappers/tmp"

    # create Folder with unique name '1234' inside the parent_directory
    opportunity_Id = 1234
    folder_created_path = createFolder(folder_name=opportunity_Id , parent_dir=parent_dir)
    all_Urls = ['https://omextemplates.content.office.net/support/templates/en-us/tf16402488.dotx' ,
                'https://procurement-notices.undp.org/view_file.cfm?doc_id=257280']

    if folder_created_path :
        # we created folder, we store all files in it
        all_files_path = []
        for eachUrl in all_Urls :
            downloadUrl = eachUrl
            req = requests.get(downloadUrl)
            if req.status_code == 200 :
                filename = req.url[downloadUrl.rfind('/') + 1 :]

                # adding file path to all_files_path[] list. file just downloaded successfully
                downloaded_file_path = download_file(downloadUrl , folder_created_path ,
                                                     filename_to_be_download=filename)
                if downloaded_file_path :
                    all_files_path.append(downloaded_file_path)
                else :
                    print("file not downloaded")
            else :
                print("status code is not 200")

        # loop through all files that created and create zip
        if len(all_files_path) > 0 :
            # writing files to a zipfile
            with ZipFile(os.path.join(parent_dir , f"{opportunity_Id}.zip") , 'w' ,
                         compression=zipfile.ZIP_DEFLATED) as zip :
                # writing each file one by one
                for file in all_files_path :
                    zip.write(file)
        else :
            print("no files to zip them")
    else :
        print("error while creating folder")

the above script works fine for the first URL inside the all_Urls list. but it does not work for the second URL. I noticed the second URL does not have the file name in it instead the file will download automatically if I put the send use it in the browser URL. how to download files from such a URL and zip them along with my other files

kindly look at enter link description here question as well how

Downloading Files from URLs and zip downloaded files in python

0 Answers0

Linked