Refactor, simplify, more error handling

This commit is contained in:
iamdoubz
2026-04-06 16:49:55 -05:00
parent 90cfe009b6
commit 86969ffff7
+395 -276
View File
@@ -1,5 +1,4 @@
import argparse import argparse
import glob
import logging import logging
import os import os
from pathlib import Path from pathlib import Path
@@ -16,11 +15,12 @@ from selenium.webdriver.support.ui import WebDriverWait, Select
from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support import expected_conditions as EC
import sys import sys
import time import time
import traceback
__version__ = "2026.3.27.0" __version__ = "2026.4.2.0"
# Helper for logging # Helper for logging
def setup_logging(mode="syslog", logfile=None): def setup_logging(folder, mode="syslog", logfile=None):
logger = logging.getLogger() logger = logging.getLogger()
logger.setLevel(logging.INFO) logger.setLevel(logging.INFO)
# remove default handlers # remove default handlers
@@ -39,36 +39,381 @@ def setup_logging(mode="syslog", logfile=None):
if mode in ("file", "all"): if mode in ("file", "all"):
if not logfile: if not logfile:
raise ValueError("File logging requires a logfile path") raise ValueError("File logging requires a logfile path")
file_handler = logging.FileHandler(logfile) file_handler = logging.FileHandler(os.path.join(folder, logfile))
file_handler.setFormatter(formatter) file_handler.setFormatter(formatter)
logger.addHandler(file_handler) logger.addHandler(file_handler)
# Setup pass in arguments # Create the parser and add a description
def main(): def args():
# Create the parser and add a description
parser = argparse.ArgumentParser( parser = argparse.ArgumentParser(
description="V-dlp options and variables...", description="V-dlp options and variables...",
epilog="End of help documentation..." epilog="End of help documentation..."
) )
#parser = argparse.ArgumentParser()
parser.add_argument("-l", type=str, help="Choose logging option", default="syslog", choices=["syslog","file","all","none"]) 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("-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("-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("-u", type=str, help="File with links inside", default="urls.txt")
parser.add_argument("-uh", type=bool, help="Use headless Chrome", default=False) 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("-tl", type=float, help="How long to wait for webpage to load before timeout", default=8)
parser.add_argument("-r", type=float, help="How often to refresh statistics on screen", default=2) 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("-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("-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("-gc", type=int, help="Download cover image (0: don't download, 1: small (avif), 2: large (webp), 3: both)", default=0, choices=[0, 1, 2, 3])
parser.add_argument("-v", action='store_true', help="Display version information") parser.add_argument("-v", action='store_true', help="Display version information")
args = parser.parse_args() return parser
if args.v: # URLs to process
sys.exit(f"v{__version__}\n") def open_urls(file):
try:
with open(file) as f:
urls = [line.strip() for line in f]
urls = list(dict.fromkeys(urls))
url_length = len(urls)
ess = "s"
if url_length == 0:
logging.warning("There are no URLs to process!")
sys.exit("There are no URLs to process!")
if url_length == 1:
ess = ""
logging.info(f"Will process {url_length} URL{ess}...")
return urls, url_length
except Exception as e:
exc_type, exc_obj, exc_tb = sys.exc_info()
emessage = f"Error {exc_tb.tb_lineno}: Could not find url file: {e}!"
logging.error(emessage)
sys.exit(emessage)
setup_logging(args.l, args.lf) # Launch Chrome
def open_chrome(headless, download_dir):
# Generate list of random screen resolutions
display_resolutions = ["2560,1440","1920,1080","1600,1200"]
# Create and add Chrome options
chrome_options = Options()
if headless == True:
chrome_options.add_argument("--headless=new")
chrome_options.add_argument("--disable-gpu")
chrome_options.add_argument(f"--window-size=2560,1440")
chrome_options.add_argument("--no-sandbox")
chrome_options.add_argument("--disable-dev-shm-usage")
chrome_options.add_argument("--simulate-outdated-no-au='Tue, 31 Dec 2099 23:59:59 GMT'")
chrome_options.add_argument("--disable-background-networking")
chrome_options.add_argument("--disable-component-update")
prefs = {
"download.default_directory": download_dir,
"download.prompt_for_download": False,
"download.directory_upgrade": True
}
chrome_options.add_experimental_option("prefs", prefs)
driver = webdriver.Chrome(options=chrome_options)
# Chrome sometimes blocks downloads in headless mode
if headless == True:
driver.execute_cdp_cmd(
"Page.setDownloadBehavior",
{
"behavior": "allow",
"downloadPath": download_dir
}
)
return driver
# Helper to calculate percentages
def percentage_of_total(part, whole):
if whole == 0:
return 0 # Handle division by zero case
return round(((part / whole) * 100), 1)
# Check for temp files limiting amount of time spent before failing
def wait_for_file(download_dir, check_interval_seconds=0.25, max_wait_seconds=10):
start_time = time.time()
while True:
# Check if the file exists
files = os.listdir(download_dir)
partial = [f for f in files if f.endswith(".crdownload")]
if partial:
elapsed_time = time.time() - start_time
return True
# Calculate elapsed time and check if timeout is reached
elapsed_time = time.time() - start_time
if elapsed_time >= max_wait_seconds:
print(f"Timed out after {max_wait_seconds} seconds. Temp file not found at {download_dir}.")
return False
# Wait for the specified interval before the next check
remaining_time = max_wait_seconds - elapsed_time
if remaining_time < check_interval_seconds:
time_to_sleep = remaining_time
# Time to sleep
time.sleep(check_interval_seconds)
# Display useful stats about ongoing downloads
def monitor_download(folder, fsize, refresh_rate, tstart=time.time()):
downloading = True
last_size = 0
while downloading:
files = os.listdir(folder)
partial = [f for f in files if f.endswith(".crdownload")]
if partial:
file_path = os.path.join(folder, partial[0])
size = os.path.getsize(file_path)
tot_perc = percentage_of_total(size, fsize)
if size != last_size:
ct = time.time()
dt = ct - tstart
if dt == 0:
dt = 1
speed = round(((size - last_size)/1024/1024/refresh_rate)*8, 2)
etas = ((fsize - size) / (size / dt))
etam, etams = divmod(etas, 60)
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)
else:
downloading = False
tsec = time.time() - tstart
if tsec == 0:
tsec = 1
tmin, tmsec = divmod(tsec, 60)
avg_speed = round((fsize/tsec/1024/1024)*8, 1)
if avg_speed > 175:
logging.warning("Download did not start (probably)")
return -999, -999
else:
logging.info(f"Downloaded {round((fsize/1024/1024), 2)}MB in {int(tmin)}m {int(tmsec)}s ({avg_speed} Mbps).")
return last_size, tsec
# Get cover art
def download_img(driver, download_dir, title, itype, baseurl):
try:
img_element = WebDriverWait(driver, 5).until(
EC.presence_of_element_located((By.XPATH, '//img[@alt="Box"]'))
)
if img_element:
if itype in [1,3]:
img_url = img_element.get_attribute('src')
if img_url:
img_saved = save_img(download_dir, title, itype, img_url, baseurl, 1)
if not img_saved:
logging.warning("See above WARNING.")
else:
logging.warning("No box image url found.")
if itype in [2,3]:
body_element = driver.find_element(By.ID, "main")
img_element.click()
try:
dialog_element = WebDriverWait(driver, 5).until(
EC.presence_of_element_located((By.ID, "imageDialog"))
)
if dialog_element:
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()
time.sleep(1)
except Exception as e:
exc_type, exc_obj, exc_tb = sys.exc_info()
logging.warning(f"Error {exc_tb.tb_lineno}: No large box image found!")
except Exception as e:
exc_type, exc_obj, exc_tb = sys.exc_info()
logging.warning(f"Error {exc_tb.tb_lineno}: No box image exists. Skipping...")
# Save cover art
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'{iurl}'
}
response = requests.get(iurl, headers=headers, allow_redirects=True, stream=True)
response.raise_for_status()
if response.status_code == 200:
fext = 'avif'
ftitle = sanitize_filename(title)
if iform == 2:
fext = 'webp'
save_path = os.path.join(f"{download_dir}", f"{ftitle}.{fext}")
with open(save_path, 'wb') as file:
for chunk in response.iter_content(1024):
file.write(chunk)
return True
else:
logging.warning(f"Could not download box image: {response.status_code} - {response.reason}")
return False
# Download logic
def download_it(driver, wait, monitor, wait_time, download_dir, refresh_rate, total_size, total_time, cur_url, url_length, dtitle, durl, cover, failed_urls, ddisc=0):
# Get file size
size = 0
try:
size_element = wait.until(
EC.presence_of_element_located((By.ID, "dl_size"))
)
size_raw = size_element.text
except:
exc_type, exc_obj, exc_tb = sys.exc_info()
logging.warning(f"Error {exc_tb.tb_lineno}: Could not determine download size from webpage")
size_raw = '1 GB'
pass
logging.info(f"{dtitle} {size_raw}")
# Download box cover
if cover > 0:
raw_title = driver.title.replace("The Vault: ", "")
download_img(driver, download_dir, raw_title, cover, durl)
# Click Download button
dl_start = time.time()
try:
download_form = wait.until(
EC.presence_of_element_located((By.ID, "dl_form"))
)
download_button = wait.until(
EC.element_to_be_clickable((By.XPATH, "//button[text()='Download']"))
)
actions = ActionChains(driver)
if download_form:
actions.move_to_element_with_offset(download_form, random.randint(1, 50), random.randint(1, 11)).perform()
time.sleep(1)
actions.move_to_element_with_offset(download_button, random.randint(1, 25), random.randint(1, 6)).perform()
time.sleep(0.5)
#time.sleep(3)
download_form = wait.until(
EC.presence_of_element_located((By.ID, "dl_form"))
)
#logging.info("Clicked form submit")
if download_form:
download_form.submit()
raw_title = driver.title
if raw_title == "Vimm's Lair: Error 400":
return -998, -998
else:
raise ValueError("Download form could not be submitted")
else:
actions.move_to_element_with_offset(download_button, random.randint(1, 13), random.randint(1, 3)).perform()
time.sleep(1)
#logging.info("Clicked download button")
download_button = wait.until(
EC.element_to_be_clickable((By.XPATH, "//button[text()='Download']"))
)
if download_button:
download_button.click()
#driver.execute_script("arguments[0].click();", download_button)
raw_title = driver.title
if raw_title == "Vimm's Lair: Error 400":
return -998, -998
else:
raise ValueError("Download button could not be submitted")
dl_start = time.time()
except Exception as e:
exc_type, exc_obj, exc_tb = sys.exc_info()
logging.warning(f"Error {exc_tb.tb_lineno}: Download button not found for {dtitle}!")
logging.error(f"{e}")
failed_urls.append(dtitle)
failed_urls.append(durl)
return 0, 0
# Convert human readable size to bytes
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 ** 2
# Monitor current download
argmonitor = monitor
argwait = wait_time
ctime = 0
csize = 0
# If file size is >32MB, go ahead and monitor anyway
if size > 33554431 and monitor:
monitor = False
# If file size <32MB, force no monitor
if size < 33554432:
monitor = True
wait_time = 15
size_limit = 2097152
size_factor = size // size_limit
if size_factor < wait_time:
wait_time = size_factor
if size_factor == 0:
wait_time = 1
# If we are monitoring downloads
if monitor == False:
if wait_for_file(download_dir, 0.25, 8):
csize, ctime = monitor_download(download_dir, size*1.01, refresh_rate, dl_start)
if csize == -999 and ctime == -999:
failed_urls.append(dtitle)
failed_urls.append(durl)
elif csize == -998 and ctime == -998:
logging.warning("Vimm's Lair Error 400: An unexpected browser error has occurred (we think you might be a bot)")
failed_urls.append(dtitle)
failed_urls.append(durl)
else:
total_size += csize
total_time += ctime
else:
# Try to click Continue if it appears
try:
raw_title = driver.title
if raw_title != "Vimm's Lair: Error 400":
continue_button = WebDriverWait(driver, 4).until(
EC.element_to_be_clickable((By.XPATH, "//input[@value='Continue']"))
)
continue_button.click()
dl_start = time.time()
logging.info(f"DL Click: {dl_start} Check: {round((time.time() - dl_start),1)}")
if wait_for_file(files, 0.25, 8):
csize, ctime = monitor_download(download_dir, files, size*1.01, refresh_rate, dl_start)
total_size += csize
total_time += ctime
else:
logging.warning("Never found temp file for download...")
failed_urls.append(dtitle)
failed_urls.append(durl)
pass
else:
logging.warning("Vimm's Lair Error 400: An unexpected browser error has occurred (we think you might be a bot)")
failed_urls.append(dtitle)
failed_urls.append(durl)
except:
exc_type, exc_obj, exc_tb = sys.exc_info()
logging.warning(f"Error {exc_tb.tb_lineno}: Could not click on Continue button...")
failed_urls.append(dtitle)
failed_urls.append(durl)
pass
# 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
# Main program
def main(args):
download_dir = args.d download_dir = args.d
url_file = args.u url_file = args.u
headless = args.uh headless = args.uh
@@ -81,266 +426,22 @@ def main():
logging.info(f"Download Directory: {download_dir}") logging.info(f"Download Directory: {download_dir}")
logging.info(f"Reading URLs from: {url_file}") logging.info(f"Reading URLs from: {url_file}")
emessage = f"" urls, url_length = open_urls(url_file)
# URLs to process
try:
with open(url_file) as f:
urls = [line.strip() for line in f]
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"
if url_length == 0:
logging.warning("There are no URLs to process!")
sys.exit("There are no URLs to process!")
if url_length == 1:
ess = ""
logging.info(f"Will process {url_length} URL{ess}...")
# If directory does not exist, create it
os.makedirs(download_dir, exist_ok=True)
# Generate list of random screen resolutions
display_resolutions = ["2560,1440","1920,1080","1600,1200"]
# Create and add Chrome options
chrome_options = Options()
if headless == True:
chrome_options.add_argument("--headless=new")
chrome_options.add_argument("--disable-gpu")
chrome_options.add_argument(f"--window-size=2560,1440")
chrome_options.add_argument("--no-sandbox")
chrome_options.add_argument("--disable-dev-shm-usage")
prefs = {
"download.default_directory": download_dir,
"download.prompt_for_download": False,
"download.directory_upgrade": True
}
chrome_options.add_experimental_option("prefs", prefs)
driver = webdriver.Chrome(options=chrome_options) # For each URL in the file
if headless == True:
# Chrome sometimes blocks downloads in headless mode
driver.execute_cdp_cmd(
"Page.setDownloadBehavior",
{
"behavior": "allow",
"downloadPath": download_dir
}
)
# Helper to calculate percentages
def percentage_of_total(part, whole):
if whole == 0:
return 0 # Handle division by zero case
return round(((part / whole) * 100), 1)
# Display useful stats about ongoing downloads
def monitor_download(folder, fsize):
downloading = True
last_size = 0
tstart = time.time()
while downloading:
files = os.listdir(folder)
partial = [f for f in files if f.endswith(".crdownload")]
if partial:
file_path = os.path.join(folder, partial[0])
size = os.path.getsize(file_path)
tot_perc = percentage_of_total(size, fsize)
if size != last_size:
ct = time.time()
dt = ct - tstart
if dt == 0:
dt = 1
speed = round(((size - last_size)/1024/1024/refresh_rate)*8, 2)
etas = ((fsize - size) / (size / dt))
etam, etams = divmod(etas, 60)
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)
else:
downloading = False
tsec = time.time() - tstart
if tsec == 0:
tsec = 1
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
while not glob.glob(pattern):
time.sleep(delay)
i += 1
if i > max:
break
# Return the first matching file
return glob.glob(pattern)[0]
# For each URL in the file, run program
total_size = 0 total_size = 0
total_time = 0 total_time = 0
cur_url = 1
failed_urls = [] failed_urls = []
for url in urls: for url in urls:
def download_it(monitor, wait_time, download_dir, total_size, total_time, cur_url, dtitle, durl, cover, ddisc=0): # Launch chrome and open URL
def download_img(download_dir, title, itype, baseurl): driver = open_chrome(headless, download_dir)
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'
ftitle = sanitize_filename(title)
if iform == 2:
fext = 'webp'
save_path = os.path.join(f"{download_dir}", f"{ftitle}.{fext}")
with open(save_path, 'wb') as file:
for chunk in response.iter_content(1024):
file.write(chunk)
time.sleep(1)
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()
time.sleep(1)
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 > 33554431 and monitor:
monitor = False
if size < 33554432:
monitor = True
wait_time = 15
if size < 2097152 * 10:
wait_time = 10
if size < 2097152 * 8:
wait_time = 8
if size < 2097152 * 7:
wait_time = 7
if size < 2097152 * 6:
wait_time = 6
if size < 2097152 * 5:
wait_time = 5
if size < 2097152 * 4:
wait_time = 4
if size < 2097152 * 3:
wait_time = 3
if size < 2097152 * 2:
wait_time = 2
if size < 2097152:
wait_time = 1
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) driver.get(url)
# Wait to open URL # Wait to open URL
wait = WebDriverWait(driver, page_load_time) wait = WebDriverWait(driver, page_load_time)
# Multiple discs?
# Check for multiple discs
try: try:
disc_element = driver.find_element(By.ID, "disc_number") disc_element = driver.find_element(By.ID, "disc_number")
disc_select = Select(disc_element) disc_select = Select(disc_element)
@@ -353,32 +454,50 @@ def main():
disc_replace = f"{cur_url}/{url_length}: " disc_replace = f"{cur_url}/{url_length}: "
disc_select.select_by_value(disc_value) disc_select.select_by_value(disc_value)
title = driver.title.replace("The Vault: ", disc_replace) 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) osize, otime = download_it(driver, wait, monitor, wait_time, download_dir, refresh_rate, total_size, total_time, cur_url, url_length, title, url, cover, failed_urls, disc_value)
total_size += osize total_size += osize
total_time += otime total_time += otime
cur_url += 1 cur_url += 1
except: except KeyboardInterrupt:
logging.info("\nSignal received. Shutting down gracefully...")
driver.close()
driver.quit()
sys.exit(67)
except Exception as e:
logging.warning(f"Multiple discs error? {e}")
title = driver.title.replace("The Vault: ", f"{cur_url}/{url_length}: ") 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) osize, otime = download_it(driver, wait, monitor, wait_time, download_dir, refresh_rate, total_size, total_time, cur_url, url_length, title, url, cover, failed_urls)
total_size += osize total_size += osize
total_time += otime total_time += otime
cur_url += 1 cur_url += 1
# Close Chrome session finally:
driver.quit() # Close and end Chrome session
driver.close()
driver.quit()
# If we were monitoring, display total statistics
if total_size > 0: if total_size > 0:
if total_time == 0: if total_time == 0:
total_time = 1 total_time = 1
ttmin, ttmsec = divmod(total_time, 60) ttmin, ttmsec = divmod(total_time, 60)
tavg_speed = round((total_size/total_time/1024/1024)*8, 1) 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).") logging.info(f"Downloaded {round((total_size/1024/1024), 2)}MB in {int(ttmin)}m {int(ttmsec)}s ({tavg_speed} Mbps).")
# If anything failed, write to file
if failed_urls: if failed_urls:
# Add URL links to a file fn = os.path.join(f"{download_dir}", "failed.txt")
fn = f"failed_downloads.txt" logging.warning(f"Appending failed downloads to {fn}")
logging.warning(f"Writing failed downloads to {fn}") fnt = "a"
fnt = 'a'
with open(f"{fn}", fnt) as f: with open(f"{fn}", fnt) as f:
for item in failed_urls: for item in failed_urls:
f.write(item + '\n') f.write(item + '\n')
if __name__ == "__main__": if __name__ == "__main__":
main() parser = args()
args = parser.parse_args()
if args.v:
sys.exit(f"v{__version__}\n")
# If directory does not exist, create it
os.makedirs(args.d, exist_ok=True)
setup_logging(args.d, args.l, args.lf)
main(args)