Add -gc argument to V-dlp program

README.md

@@ -55,32 +55,33 @@ V-dlp will parse a file and attempt to download each one at a time.
 | -tw | Number of seconds to pause between downloads | float | 4 |
 | -nm | Do not monitor download statistics (set flag to True for small downloads <32MB) | boolean | False |
 | -uh | Use headless Chrome (If you do not want to use, do not pass in the flag) | boolean | False |
+| -gc | Download cover image (0: don't download, 1: small, 2: large, 3: both) | int | 0 |
 | -v | Display version information | NA | none |
 
 ## Features
 
 - [X] Download files
+- [X] Handle multi-disc downloads
+- [X] Download box cover art
 - [X] Show download statistics (speed, ETA)
+- [X] More download statistics
 - [X] Show number of URLs
 - [X] Show download name/size
 - [X] Add headless option
+- [X] Show failed downloads
+- [X] Remove duplicate URLs
+- [X] Get all links (#, A-Z)
 - [X] No more waiting for each download to finish
 
-
 ## Upcoming features
 
 - [ ] Proper error handling
-- [ ] Show failed downloads
-- [ ] Download cover art
 - [ ] Download manuals
-- [ ] Remove duplicate URLs
 - [ ] Email upon completion
-- [ ] More download statistics
-- [ ] Handle multi-disc downloads
 - [ ] Remove dependency on external start of Chrome Driver
 - [ ] Click on ads
 - [ ] OS agnostic (heavily Windows based as they need the most hand holding)
-- [ ] Get # links
+
 
 ## Bonus
 

dlp.py

@@ -4,16 +4,19 @@ import logging
 import os
 from pathlib import Path
 import random
+import requests
 from selenium import webdriver
+from selenium.webdriver.common.action_chains import ActionChains
 from selenium.webdriver.common.by import By
+from selenium.common.exceptions import NoSuchElementException
 from selenium.webdriver.chrome.service import Service
 from selenium.webdriver.chrome.options import Options
-from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support.ui import WebDriverWait, Select
 from selenium.webdriver.support import expected_conditions as EC
 import sys
 import time
 
-__version__ = "2026.3.24.0"
+__version__ = "2026.3.25.0"
 
 # Helper for logging
 def setup_logging(mode="syslog", logfile=None):
@@ -47,44 +50,49 @@ def main():
         epilog="End of help documentation..."
     )
     #parser = argparse.ArgumentParser()
-    parser.add_argument("--log", "-l", type=str, help="Choose logging option", default="syslog", choices=["syslog","file","all","none"])
-    parser.add_argument("--logfile", "-lf", help="If log is file/all need to specify file to log to")
-    parser.add_argument("--dir_download", "-d", type=str, help="Download directory to use", default=f"{Path.home() / 'Downloads'}")
-    parser.add_argument("--file_urls", "-u", type=str, help="File with links inside", default="urls.txt")
-    parser.add_argument("--chrome_port", "-p", type=float, help="Specify already running Chrome Driver port", default=54321)
-    parser.add_argument("--use_headless", "-uh", type=bool, help="Use headless Chrome", default=False)
-    parser.add_argument("--page_load_time", "-tl", type=float, help="How long to wait for webpage to load before timeout", default=10)
-    parser.add_argument("--refresh_rate", "-r", type=float, help="How often to refresh statistics on screen", default=2)
-    parser.add_argument("--wait_time", "-tw", type=float, help="Number of seconds to pause between downloads", default=4)
-    parser.add_argument("--no_monitor", "-nm", type=bool, help="Do not monitor download statistics", default=False)
-    parser.add_argument("--version", "-v", action='store_true', help="Display version information")
+    parser.add_argument("-l", type=str, help="Choose logging option", default="syslog", choices=["syslog","file","all","none"])
+    parser.add_argument("-lf", help="If log is file/all need to specify file to log to")
+    parser.add_argument("-d", type=str, help="Download directory to use", default=f"{Path.home() / 'Downloads'}")
+    parser.add_argument("-u", type=str, help="File with links inside", default="urls.txt")
+    parser.add_argument("-p", type=float, help="Specify already running Chrome Driver port", default=54321)
+    parser.add_argument("-uh", type=bool, help="Use headless Chrome", default=False)
+    parser.add_argument("-tl", type=float, help="How long to wait for webpage to load before timeout", default=10)
+    parser.add_argument("-r", type=float, help="How often to refresh statistics on screen", default=2)
+    parser.add_argument("-tw", type=float, help="Number of seconds to pause between downloads", default=4)
+    parser.add_argument("-nm", type=bool, help="Do not monitor download statistics", default=False)
+    parser.add_argument("-gc", type=int, help="Download cover image (0: don't download, 1: small, 2: large, 3: both)", default=0, choices=[0, 1, 2, 3])
+    parser.add_argument("-v", action='store_true', help="Display version information")
     args = parser.parse_args()
     
-    if args.version:
+    if args.v:
         sys.exit(f"v{__version__}\n")
 
-    setup_logging(args.log, args.logfile)
+    setup_logging(args.l, args.lf)
 
-    download_dir = args.dir_download
-    url_file = args.file_urls
-    chrome_port = args.chrome_port
-    headless = args.use_headless
-    page_load_time = args.page_load_time
-    refresh_rate = args.refresh_rate
-    wait_time = args.wait_time
-    monitor = args.no_monitor
+    download_dir = args.d
+    url_file = args.u
+    chrome_port = args.p
+    headless = args.uh
+    page_load_time = args.tl
+    refresh_rate = args.r
+    wait_time = args.tw
+    monitor = args.nm
+    cover = args.gc
     
     logging.info(f"Download Directory: {download_dir}")
     logging.info(f"Reading URLs from: {url_file}")
     logging.info(f"Using ChromeD Port: {chrome_port}")
 
+    emessage = f""
     # URLs to process
     try:
         with open(url_file) as f:
             urls = [line.strip() for line in f]
-    except:
-        logging.error(f"Could not find url file: {url_file}!")
-        raise FileNotFoundError(f"Could not find url file: {url_file}!")
+    except Exception as e:
+        emessage = f"Could not find url file: {e}!"
+        logging.error(emessage)
+        sys.exit(emessage)
+    urls = list(dict.fromkeys(urls))
     url_length = len(urls)
     cur_url = 1
     ess = "s"
@@ -153,7 +161,7 @@ def main():
                     speed = round(((size - last_size)/1024/1024/refresh_rate)*8, 2)
                     etas = ((fsize - size) / (size / dt))
                     etam, etams = divmod(etas, 60)
-                    if args.log in ("syslog", "all"):
+                    if args.l in ("syslog", "all"):
                         print(F"Downloading at {speed} Mbps... {tot_perc}%. ETA: {int(etam)}m {int(etams)}s       ", end="\r")
                 last_size = size
                 time.sleep(refresh_rate)
@@ -165,6 +173,7 @@ def main():
                 tmin, tmsec = divmod(tsec, 60)
                 avg_speed = round((fsize/tsec/1024/1024)*8, 1)
                 logging.info(f"Downloaded {round((fsize/1024/1024), 2)}MB in {int(tmin)}m {int(tmsec)}s ({avg_speed} Mbps).")
+                return last_size, tsec
     def wait_for_file(pattern, delay=1, max=15):
         #print(f"Waiting for file matching: {pattern}...")
         i = 0
@@ -176,70 +185,185 @@ def main():
         # Return the first matching file
         return glob.glob(pattern)[0]
     # For each URL in the file, run program
+    total_size = 0
+    total_time = 0
+    failed_urls = []
     for url in urls:
+        def download_it(monitor, wait_time, download_dir, total_size, total_time, cur_url, dtitle, durl, cover, ddisc=0):
+            def download_img(download_dir, title, itype, baseurl):
+                def save_img(download_dir, title, itype, iurl, baseurl, iform):
+                    headers: dict[str, str] = {
+                        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+                        'Accept-Encoding': 'gzip, deflate, br, zstd',
+                        'Connection': 'keep-alive',
+                        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:149.0) Gecko/20100101 Firefox/149.0',
+                        'Referer': f'{url}'
+                    }
+                    response = requests.get(iurl, headers=headers, allow_redirects=True, stream=True)
+                    response.raise_for_status()
+                    if response.status_code == 200:
+                        fext = 'avif'
+                        if iform == 2:
+                            fext = 'webp'
+                        save_path = os.path.join(download_dir, f"{title}.{fext}")
+                        with open(save_path, 'wb') as file:
+                            for chunk in response.iter_content(1024):
+                                file.write(chunk)
+                    else:
+                        logging.warning(f"Could not download box image: {response.status_code} - {response.reason}")
+                        pass
+                try:
+                    img_element = WebDriverWait(driver, 5).until(
+                        EC.presence_of_element_located((By.XPATH, '//img[@alt="Box"]'))
+                    )
+                    if itype in [1,3]:
+                        img_url = img_element.get_attribute('src')
+                        if img_url:
+                            save_img(download_dir, title, itype, img_url, baseurl, 1)
+                        else:
+                            logging.warning("No box image url found.")
+                    if itype in [2,3]:
+                        body_element = driver.find_element(By.TAG_NAME, "body")
+                        img_element.click()
+                        try:
+                            dialog_element = WebDriverWait(driver, 5).until(
+                                EC.presence_of_element_located((By.ID, "imageDialog"))
+                            )
+                            img_element2 = dialog_element.find_element(By.TAG_NAME, "img")
+                            img_url2 = img_element2.get_attribute('src')
+                            if img_url2:
+                                save_img(download_dir, title, itype, img_url2, baseurl, 2)
+                            else:
+                                logging.warning("No large box image found.")
+                            actions = ActionChains(driver)
+                            actions.move_to_element_with_offset(body_element, random.randint(1, 100), random.randint(1, 100)).click().perform()
+                        except Exception as e:
+                            logging.warning(f"No large box image found! {e}")
+                except:
+                    logging.warning("No box image exists. Skipping...")
+            # Get Vimm file size
+            size = 0
+            try:
+                size_element = WebDriverWait(driver, 5).until(
+                    EC.presence_of_element_located((By.ID, "dl_size"))
+                )
+                size_raw = size_element.text
+            except:
+                logging.warning("Could not determine download size from webpage")
+                size_raw = '1 GB'
+                pass
+            logging.info(f"{title} {size_raw}")
+            # Download box cover
+            if cover > 0:
+                raw_title = driver.title.replace("The Vault: ", "")
+                download_img(download_dir, raw_title, cover, url)
+            # Click Download button
+            try:
+                download_button = WebDriverWait(driver, 5).until(
+                    EC.element_to_be_clickable((By.XPATH, "//button[text()='Download']"))
+                )
+                download_button.click()
+            except:
+                logging.warning(f"Download button not found for {title}!")
+                failed_urls.append(url)
+                pass
+            if " KB" in size_raw:
+                size = float(size_raw.replace(" KB", "")) * 1024
+            elif " MB" in size_raw:
+                size = float(size_raw.replace(" MB", "")) * 1024 ** 2
+            elif " GB" in size_raw:
+                size = float(size_raw.replace(" GB", "")) * 1024 ** 3
+            elif " TB" in size_raw:
+                size = float(size_raw.replace(" TB", "")) * 1024 ** 4
+            else:
+                size = 500 * 1024 * 1024
+            # Try to click Continue if it appears
+            try:
+                continue_button = WebDriverWait(driver, 5).until(
+                    EC.element_to_be_clickable((By.XPATH, "//input[@value='Continue']"))
+                )
+                continue_button.click()
+            except:
+                pass
+            # Monitor current download
+            argmonitor = monitor
+            argwait = wait_time
+            ctime = 0
+            csize = 0
+            if size < 33554432:
+                monitor = True
+                wait_time = 15
+                if total_size > 0 and total_time > 0:
+                    wait_time = min((size / total_size / total_time) * 1.25, wait_time)
+            if monitor == False:
+                tempTime = time.time()
+                file_pattern = download_dir + '/*.crdownload'
+                while not os.path.exists(wait_for_file(file_pattern)):
+                    if time.time() - tempTime > wait_time:
+                        logging.warning("Never found temp file for download...")
+                        break
+                    else:
+                        logging.warning(f"{time.time() - tempTime}")
+                        time.sleep(refresh_rate)
+            if monitor == False:
+                csize, ctime = monitor_download(download_dir, size*1.01)
+                total_size += csize
+                total_time += ctime
+            # Wait to call next URL
+            if cur_url < url_length:
+                if size < 33554432:
+                    logging.warning(f"File size was too small to monitor! (Less than 32MB). Waiting {round(wait_time, 1)} seconds...")
+                time.sleep(wait_time)
+            else:
+                if size < 33554432:
+                    logging.warning(f"File size was too small to monitor! (Less than 32MB).")
+            cur_url += 1
+            monitor = argmonitor
+            wait_time = argwait
+            return csize, ctime
         # Open URL
         driver.get(url)
         # Wait to open URL
         wait = WebDriverWait(driver, page_load_time)
-        # Click Download button
-        download_button = wait.until(
-            EC.element_to_be_clickable((By.XPATH, "//button[text()='Download']"))
-        )
-        download_button.click()
-        # Output page title to console
-        title = driver.title.replace("The Vault: ", f"{cur_url}/{url_length}: ")
-        # Get Vimm file size
-        size_element = WebDriverWait(driver, 10).until(
-            EC.presence_of_element_located((By.ID, "dl_size"))
-        )
-        size_raw = size_element.text
-        logging.info(f"{title} {size_raw}")
-        size = 0
-        if " KB" in size_raw:
-            size = float(size_raw.replace(" KB", "")) * 1024
-        elif " MB" in size_raw:
-            size = float(size_raw.replace(" MB", "")) * 1024 ** 2
-        elif " GB" in size_raw:
-            size = float(size_raw.replace(" GB", "")) * 1024 ** 3
-        elif " TB" in size_raw:
-            size = float(size_raw.replace(" GB", "")) * 1024 ** 4
-        else:
-            size = 500 * 1024 * 1024
-        # Try to click Continue if it appears
+        # Multiple discs?
         try:
-            continue_button = WebDriverWait(driver, 4).until(
-                EC.element_to_be_clickable((By.XPATH, "//input[@value='Continue']"))
-            )
-            continue_button.click()
+            disc_element = driver.find_element(By.ID, "disc_number")
+            disc_select = Select(disc_element)
+            url_length += len(disc_select.options) - 1
+            for option in disc_select.options:
+                disc_value = option.get_attribute("value")
+                disc_text = option.get_attribute("text")
+                disc_replace = f"{cur_url}/{url_length}: ({disc_text}) "
+                if len(disc_select.options) == 1:
+                    disc_replace = f"{cur_url}/{url_length}: "
+                disc_select.select_by_value(disc_value)
+                title = driver.title.replace("The Vault: ", disc_replace)
+                osize, otime = download_it(monitor, wait_time, download_dir, total_size, total_time, cur_url, title, url, cover, disc_value)
+                total_size += osize
+                total_time += otime
+                cur_url += 1
         except:
-            pass
-
-        # Monitor current download
-        argmonitor = monitor
-        argwait = wait_time
-        if size < 33554432:
-            monitor = True
-            wait_time = 17
-            logging.warning("File size was too small to monitor! (Less than 32MB)")
-        if monitor == False:
-            tempTime = time.time()
-            file_pattern = download_dir + '/*.crdownload'
-            while not os.path.exists(wait_for_file(file_pattern)):
-                if time.time() - tempTime > wait_time:
-                    logging.warning("Never found temp file for download...")
-                    break
-                else:
-                    logging.warning(f"{time.time() - tempTime}")
-                    time.sleep(refresh_rate)
-        if monitor == False:
-            monitor_download(download_dir, size+1024)
-        # Wait to call next URL
-        time.sleep(wait_time)
-        cur_url += 1
-        monitor = argmonitor
-        wait_time = argwait
+            title = driver.title.replace("The Vault: ", f"{cur_url}/{url_length}: ")
+            osize, otime = download_it(monitor, wait_time, download_dir, total_size, total_time, cur_url, title, url, cover)
+            total_size += osize
+            total_time += otime
+            cur_url += 1
     # Close Chrome session
     driver.quit()
+    if total_size > 0:
+        if total_time == 0:
+            total_time = 1
+        ttmin, ttmsec = divmod(total_time, 60)
+        tavg_speed = round((total_size/total_time/1024/1024)*8, 1)
+        logging.info(f"Downloaded {round((total_size/1024/1024), 2)}MB in {int(ttmin)}m {int(ttmsec)}s ({tavg_speed} Mbps).")
+    if failed_urls:
+        # Add URL links to a file
+        fn = f"failed_downloads.txt"
+        logging.warning(f"Writing failed downloads to {fn}")
+        fnt = 'a'
+        with open(f"{fn}", fnt) as f:
+            for item in failed_urls:
+                f.write(item + '\n')
 
 if __name__ == "__main__":
     main()

helpers/version.txt

@@ -7,8 +7,8 @@ VSVersionInfo(
   ffi=FixedFileInfo(
     # filevers and prodvers should be always a tuple with four items: (1, 2, 3, 4)
     # Set not needed items to zero 0. Must always contain 4 elements.
-    filevers=(2026,3,24,0),
-    prodvers=(2026,3,24,0),
+    filevers=(2026,3,25,0),
+    prodvers=(2026,3,25,0),
     # Contains a bitmask that specifies the valid bits 'flags'r
     mask=0x3f,
     # Contains a bitmask that specifies the Boolean attributes of the file.
@@ -32,12 +32,12 @@ VSVersionInfo(
         u'040904B0',
         [StringStruct(u'CompanyName', u''),
         StringStruct(u'FileDescription', u'V-dlp: download a list of Vimm URLs'),
-        StringStruct(u'FileVersion', u'2026.3.24.0'),
+        StringStruct(u'FileVersion', u'2026.3.25.0'),
         StringStruct(u'InternalName', u'V-dlp'),
         StringStruct(u'LegalCopyright', u'© iamdoubz'),
         StringStruct(u'OriginalFilename', u'V-dlp.exe'),
         StringStruct(u'ProductName', u'V-dlp'),
-        StringStruct(u'ProductVersion', u'2026.3.24.0')])
+        StringStruct(u'ProductVersion', u'2026.3.25.0')])
       ]), 
     VarFileInfo([VarStruct(u'Translation', [1033, 1200])])
   ]

helpers/version_ug.txt

@@ -7,8 +7,8 @@ VSVersionInfo(
   ffi=FixedFileInfo(
     # filevers and prodvers should be always a tuple with four items: (1, 2, 3, 4)
     # Set not needed items to zero 0. Must always contain 4 elements.
-    filevers=(2026,3,24,0),
-    prodvers=(2026,3,24,0),
+    filevers=(2026,3,25,0),
+    prodvers=(2026,3,25,0),
     # Contains a bitmask that specifies the valid bits 'flags'r
     mask=0x3f,
     # Contains a bitmask that specifies the Boolean attributes of the file.
@@ -32,12 +32,12 @@ VSVersionInfo(
         u'040904B0',
         [StringStruct(u'CompanyName', u''),
         StringStruct(u'FileDescription', u'V-dlp UG: create a list of Vimm URLs'),
-        StringStruct(u'FileVersion', u'2026.3.24.0'),
+        StringStruct(u'FileVersion', u'2026.3.25.0'),
         StringStruct(u'InternalName', u'V-dlpUG'),
         StringStruct(u'LegalCopyright', u'© iamdoubz'),
         StringStruct(u'OriginalFilename', u'V-dlpUG.exe'),
         StringStruct(u'ProductName', u'V-dlpUG'),
-        StringStruct(u'ProductVersion', u'2026.3.24.0')])
+        StringStruct(u'ProductVersion', u'2026.3.25.0')])
       ]), 
     VarFileInfo([VarStruct(u'Translation', [1033, 1200])])
   ]

links.py

@@ -7,7 +7,7 @@ from selenium.webdriver.chrome.options import Options
 import string
 import sys
 
-__version__ = "2026.3.24.0"
+__version__ = "2026.3.25.0"
 
 # Helper for logging
 def setup_logging(mode="syslog", logfile=None):
@@ -98,7 +98,10 @@ def main():
     
     # Function to read platform/letter and write links to file
     def get_links(pf, lets):
-        driver.get(f"https://vimm.net/vault/{pf}/{lets}")
+        if lets in string.ascii_uppercase:
+            driver.get(f"https://vimm.net/vault/{pf}/{lets}")
+        else:
+            driver.get(f"https://vimm.net/vault/{lets}")
         data = []
         # Locate the main table
         table = driver.find_element(By.CSS_SELECTOR, "table.rounded")
@@ -149,8 +152,12 @@ def main():
             
 
     if letter == 'ALL':
+        big_list = []
+        big_list.append({"platform": platform, "letter": f"?p=list&system={platform}&section=number"})
         for l in string.ascii_uppercase:
-            get_links(platform, l)
+            big_list.append({"platform": platform, "letter": l})
+        for a in big_list:
+            get_links(a['platform'], a['letter'])
     else:
         get_links(platform, letter)
 

urls.txt

@@ -0,0 +1 @@
+https://vimm.net/vault/2829