def start_download(self) -> None:
if not self.gallery or not self.gallery.link:
return
logger.info(
"Downloading an archive from a generic HTTP server: {}".format(
self.gallery.link))
request_dict = construct_request_dict(self.settings, self.own_settings)
request_file = requests.get(self.gallery.link,
stream='True',
**request_dict)
filename = get_filename_from_cd(
request_file.headers.get('content-disposition'))
if not filename:
if self.gallery.link.find('/'):
filename = self.gallery.link.rsplit('/', 1)[1]
if not filename:
logger.error("Could not find a filename for link: {}".format(
self.gallery.link))
self.return_code = 0
self.gallery.title = filename.replace(".zip", "")
self.gallery.filename = replace_illegal_name(
available_filename(
self.settings.MEDIA_ROOT,
os.path.join(self.own_settings.archive_dl_folder, filename)))
filepath = os.path.join(self.settings.MEDIA_ROOT,
self.gallery.filename)
with open(filepath, 'wb') as fo:
for chunk in request_file.iter_content(4096):
fo.write(chunk)
self.gallery.filesize, self.gallery.filecount = get_zip_fileinfo(
filepath)
if self.gallery.filesize > 0:
self.crc32 = calc_crc32(filepath)
self.fileDownloaded = 1
self.return_code = 1
else:
logger.error("Could not download archive")
self.return_code = 0
def start_download(self) -> None:
if not self.gallery or not self.gallery.temp_archive:
return
logger.info(
"Downloading an archive: {} from a Panda Backup-like source: {}".
format(self.gallery.title, self.gallery.temp_archive['link']))
to_use_filename = get_base_filename_string_from_gallery_data(
self.gallery)
to_use_filename = replace_illegal_name(to_use_filename)
self.gallery.filename = available_filename(
self.settings.MEDIA_ROOT,
os.path.join(self.own_settings.archive_dl_folder,
to_use_filename + '.zip')) # TODO: File could be cbz.
request_dict = construct_request_dict(self.settings, self.own_settings)
request_dict['stream'] = True
request_file = request_with_retries(
self.gallery.temp_archive['link'],
request_dict,
)
if not request_file:
logger.error("Could not download archive")
self.return_code = 0
return
filepath = os.path.join(self.settings.MEDIA_ROOT,
self.gallery.filename)
with open(filepath, 'wb') as fo:
for chunk in request_file.iter_content(4096):
fo.write(chunk)
self.gallery.filesize, self.gallery.filecount = get_zip_fileinfo(
filepath)
if self.gallery.filesize > 0:
self.crc32 = calc_crc32(filepath)
self.fileDownloaded = 1
self.return_code = 1
else:
logger.error("Could not download archive")
self.return_code = 0
def start_download(self) -> None:
if not self.gallery or not self.gallery.link or not self.gallery.archiver_key:
return
to_use_filename = get_base_filename_string_from_gallery_data(
self.gallery)
to_use_filename = replace_illegal_name(to_use_filename)
self.gallery.filename = available_filename(
self.settings.MEDIA_ROOT,
os.path.join(self.own_settings.archive_dl_folder,
to_use_filename + '.zip'))
request_dict = construct_request_dict(self.settings, self.own_settings)
request_file = requests.get(self.gallery.archiver_key,
stream='True',
**request_dict)
filepath = os.path.join(self.settings.MEDIA_ROOT,
self.gallery.filename)
with open(filepath, 'wb') as fo:
for chunk in request_file.iter_content(4096):
fo.write(chunk)
self.gallery.filesize, self.gallery.filecount = get_zip_fileinfo(
filepath)
if self.gallery.filesize > 0:
self.crc32 = calc_crc32(filepath)
self.fileDownloaded = 1
self.return_code = 1
else:
logger.error("Could not download archive")
os.remove(filepath)
self.return_code = 0
def start_download(self) -> None:
if not self.gallery:
return
self.logger.info(
"Downloading an archive: {} from a Panda Backup-like source: {}".
format(self.gallery.title, self.gallery.archiver_key['link']))
self.gallery.title = replace_illegal_name(self.gallery.title)
self.gallery.filename = available_filename(
self.settings.MEDIA_ROOT,
os.path.join(self.own_settings.archive_dl_folder,
self.gallery.title + '.zip'))
request_file = requests.get(self.gallery.archiver_key['link'],
stream='True',
headers=self.settings.requests_headers,
timeout=self.settings.timeout_timer,
cookies=self.own_settings.cookies)
filepath = os.path.join(self.settings.MEDIA_ROOT,
self.gallery.filename)
with open(filepath, 'wb') as fo:
for chunk in request_file.iter_content(4096):
fo.write(chunk)
self.gallery.filesize, self.gallery.filecount = get_zip_fileinfo(
filepath)
if self.gallery.filesize > 0:
self.crc32 = calc_crc32(filepath)
self.fileDownloaded = 1
self.return_code = 1
else:
self.logger.error("Could not download archive")
self.return_code = 0
def start_download(self) -> None:
if not self.gallery:
return
to_use_filename = get_base_filename_string_from_gallery_data(
self.gallery)
to_use_filename = replace_illegal_name(to_use_filename)
self.gallery.filename = available_filename(
self.settings.MEDIA_ROOT,
os.path.join(self.own_settings.archive_dl_folder,
to_use_filename + '.zip'))
if not (self.gallery.root and self.gallery.gid and self.gallery.token
and self.gallery.archiver_key):
logger.error(
'Missing required data -> root: {}, gid: {}, token: {}, archiver_key: {}.'
.format(
self.gallery.root,
self.gallery.gid,
self.gallery.token,
self.gallery.archiver_key,
))
self.return_code = 0
return
r = self.request_archive_download(self.gallery.root, self.gallery.gid,
self.gallery.token,
self.gallery.archiver_key)
if not r:
logger.error('Could not get download link.')
self.return_code = 0
return
r.encoding = 'utf-8'
if 'Invalid archiver key' in r.text:
logger.error("Invalid archiver key received.")
self.return_code = 0
else:
archive_link = get_archive_link_from_html_page(r.text)
if archive_link == '':
logger.error(
'Could not find archive link, page text: {}'.format(
r.text))
self.return_code = 0
else:
m = re.match(r"(.*?)(\?.*?)", archive_link)
if m:
archive_link = m.group(1)
logger.info('Got link: {}, from url: {}'.format(
archive_link, r.url))
request_dict = construct_request_dict(self.settings,
self.own_settings)
request_file = requests.get(archive_link + '?start=1',
stream='True',
**request_dict)
if r and r.status_code == 200:
logger.info(
'Downloading gallery: {}.zip'.format(to_use_filename))
filepath = os.path.join(self.settings.MEDIA_ROOT,
self.gallery.filename)
with open(filepath, 'wb') as fo:
for chunk in request_file.iter_content(4096):
fo.write(chunk)
self.gallery.filesize, self.gallery.filecount = get_zip_fileinfo(
filepath)
if self.gallery.filesize > 0:
self.crc32 = calc_crc32(filepath)
self.fileDownloaded = 1
self.return_code = 1
else:
logger.error("Could not download archive")
self.return_code = 0
def start_download(self) -> None:
if not self.gallery or not self.gallery.link:
return
if self.settings.gallery_dl.executable_path:
exe_path_to_use = shutil.which(
self.settings.gallery_dl.executable_path)
else:
exe_path_to_use = shutil.which(
self.settings.gallery_dl.executable_name)
if not exe_path_to_use:
self.return_code = 0
logger.error("The gallery-dl executable was not found")
return
directory_path = mkdtemp()
arguments = ["--zip", "--dest", "{}".format(directory_path)]
if self.own_settings.proxy:
arguments.append("--proxy")
arguments.append("{}".format(self.own_settings.proxy))
if self.settings.gallery_dl.config_file:
arguments.append("--config")
arguments.append("{}".format(self.settings.gallery_dl.config_file))
if self.settings.gallery_dl.extra_arguments:
arguments.append("{}".format(
self.settings.gallery_dl.extra_arguments))
arguments.append("{}".format(self.gallery.link))
logger.info("Calling gallery-dl: {}.".format(" ".join(
[exe_path_to_use, *arguments])))
process_result = subprocess.run([exe_path_to_use, *arguments],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
universal_newlines=True)
if process_result.stderr:
self.return_code = 0
logger.error(
"An error was captured when running gallery-dl: {}".format(
process_result.stderr))
return
if process_result.returncode != 0:
self.return_code = 0
logger.error("Return code was not 0: {}".format(
process_result.returncode))
return
# If we downloaded more than one file, get the latest one
output_path = ''
file_name = ''
for (dir_path, dir_names, filenames) in os.walk(directory_path):
for current_file in filenames:
file_name = current_file
output_path = os.path.join(dir_path, current_file)
if not output_path:
self.return_code = 0
logger.error("The resulting download file was not found")
return
if not output_path or not os.path.isfile(output_path):
self.return_code = 0
logger.error(
"The resulting download file was not found: {}".format(
file_name))
return
self.gallery.filename = available_filename(
self.settings.MEDIA_ROOT,
os.path.join(self.own_settings.archive_dl_folder,
replace_illegal_name(file_name)))
self.gallery.title = os.path.splitext(file_name)[0]
filepath = os.path.join(self.settings.MEDIA_ROOT,
self.gallery.filename)
shutil.move(output_path, filepath)
shutil.rmtree(directory_path, ignore_errors=True)
self.gallery.filesize, self.gallery.filecount = get_zip_fileinfo(
filepath)
if self.gallery.filesize > 0:
self.crc32 = calc_crc32(filepath)
self.fileDownloaded = 1
self.return_code = 1
else:
logger.error("Could not download archive")
self.return_code = 0
def start_download(self) -> None:
if not self.gallery or not self.gallery.link:
return
if self.own_settings.megadl_executable_path:
exe_path_to_use = shutil.which(
self.own_settings.megadl_executable_path)
else:
exe_path_to_use = shutil.which(
self.own_settings.megadl_executable_name)
if not exe_path_to_use:
self.return_code = 0
self.logger.error("The megadl tools was not found")
return
directory_path = mkdtemp()
arguments = [
"--no-progress", "--print-names", "--path",
"{}".format(directory_path)
]
if self.own_settings.proxy:
arguments.append("--proxy")
arguments.append("{}".format(self.own_settings.proxy))
if self.own_settings.extra_megadl_arguments:
arguments.append("{}".format(
self.own_settings.extra_megadl_arguments))
arguments.append("{}".format(self.gallery.link))
self.logger.info("Calling megadl: {}.".format(" ".join(
[exe_path_to_use, *arguments])))
process_result = subprocess.run([exe_path_to_use, *arguments],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
universal_newlines=True)
message_text = process_result.stdout
if not message_text:
self.return_code = 0
self.logger.error(
"The link could not be downloaded, no output was generated after running megadl"
)
return
if process_result.stderr:
self.return_code = 0
self.logger.error(
"An error was captured when running megadl: {}".format(
process_result.stderr))
return
if "WARNING: Skipping invalid" in message_text:
self.return_code = 0
self.logger.error(
"The link could not be downloaded: {}".format(message_text))
return
# If we downloaded a folder, just take the first result
file_names = message_text.splitlines()
file_name = file_names[0]
output_path = os.path.join(directory_path, file_name)
if not os.path.isfile(output_path):
self.return_code = 0
self.logger.error(
"The resulting download file was not found: {}".format(
file_name))
return
self.gallery.filename = available_filename(
self.settings.MEDIA_ROOT,
os.path.join(self.own_settings.archive_dl_folder,
replace_illegal_name(file_name)))
self.gallery.title = os.path.splitext(file_name)[0]
filepath = os.path.join(self.settings.MEDIA_ROOT,
self.gallery.filename)
shutil.move(output_path, filepath)
shutil.rmtree(directory_path, ignore_errors=True)
self.gallery.filesize, self.gallery.filecount = get_zip_fileinfo(
filepath)
if self.gallery.filesize > 0:
self.crc32 = calc_crc32(filepath)
self.fileDownloaded = 1
self.return_code = 1
else:
self.logger.error("Could not download archive")
self.return_code = 0
def start_download(self) -> None:
if not self.gallery or not self.gallery.link:
return
to_use_filename = get_base_filename_string_from_gallery_data(self.gallery)
to_use_filename = replace_illegal_name(to_use_filename)
self.gallery.filename = available_filename(
self.settings.MEDIA_ROOT,
os.path.join(
self.own_settings.archive_dl_folder,
to_use_filename + '.zip'))
if self.gallery.content:
soup_1 = BeautifulSoup(self.gallery.content, 'html.parser')
else:
request_dict = construct_request_dict(self.settings, self.own_settings)
gallery_page = requests.get(
self.gallery.link,
**request_dict
)
soup_1 = BeautifulSoup(gallery_page.content, 'html.parser')
gallery_read = soup_1.find("a", {"class": "x-btn-rounded"})['href']
# Some URLs are really bad formatted
gallery_read = re.sub(
r'.*(' + re.escape(constants.main_page) + r'/manga/read/.+/0/1/).*', r'\1',
gallery_read,
flags=re.DOTALL
)
if not gallery_read or gallery_read in constants.bad_urls or not gallery_read.startswith(constants.main_page):
logger.warning("Reading gallery page not available, trying to guess the name.")
gallery_read = guess_gallery_read_url(self.gallery.link, self.gallery)
if not gallery_read.endswith('page/1'):
gallery_read += 'page/1'
page_regex = re.compile(r"(.*?page/)(\d+)/*$", re.IGNORECASE)
last_image = ''
directory_path = mkdtemp()
logger.info('Downloading gallery: {}'.format(self.gallery.title))
second_pass = False
while True:
try:
request_dict = construct_request_dict(self.settings, self.own_settings)
gallery_read_page = requests.get(
gallery_read,
**request_dict
)
except requests.exceptions.MissingSchema:
logger.error("Malformed URL: {}, skipping".format(gallery_read))
self.return_code = 0
shutil.rmtree(directory_path, ignore_errors=True)
return
if gallery_read_page.status_code == 404:
if gallery_read.endswith('page/1'):
if not second_pass:
gallery_read = guess_gallery_read_url(self.gallery.link, self.gallery, False)
second_pass = True
continue
logger.error("Last page was the first one: {}, stopping".format(gallery_read))
self.return_code = 0
shutil.rmtree(directory_path, ignore_errors=True)
return
# yield("Got to last gallery page, stopping")
break
soup_2 = BeautifulSoup(gallery_read_page.content, 'html.parser')
img_find = soup_2.find("img", {"class": "open"})
if not img_find:
logger.error("Gallery not available, skipping")
self.return_code = 0
shutil.rmtree(directory_path, ignore_errors=True)
return
img = img_find['src']
if last_image != '' and last_image == img:
# yield('Current image is the same as previous, skipping')
break
last_image = img
img_name = os.path.basename(img)
request_dict = construct_request_dict(self.settings, self.own_settings)
request_file = requests.get(
img,
**request_dict
)
if request_file.status_code == 404:
# yield("Got to last image, stopping")
break
with open(os.path.join(directory_path, img_name), "wb") as fo:
for chunk in request_file.iter_content(4096):
fo.write(chunk)
page_match = page_regex.search(gallery_read)
if page_match:
gallery_read = page_match.group(1) + str(int(page_match.group(2)) + 1)
else:
# yield("Could not match to change page, stopping")
break
file_path = os.path.join(
self.settings.MEDIA_ROOT,
self.gallery.filename
)
with ZipFile(file_path, 'w') as archive:
for (root_path, _, file_names) in os.walk(directory_path):
for current_file in file_names:
archive.write(
os.path.join(root_path, current_file), arcname=os.path.basename(current_file))
shutil.rmtree(directory_path, ignore_errors=True)
self.gallery.filesize, self.gallery.filecount = get_zip_fileinfo(file_path)
if self.gallery.filesize > 0:
self.crc32 = calc_crc32(file_path)
self.fileDownloaded = 1
self.return_code = 1
def start_download(self) -> None:
if not self.gallery or not self.gallery.link:
return
to_use_filename = get_base_filename_string_from_gallery_data(self.gallery)
to_use_filename = replace_illegal_name(to_use_filename)
self.gallery.filename = available_filename(
self.settings.MEDIA_ROOT,
os.path.join(
self.own_settings.archive_dl_folder,
to_use_filename + '.zip'))
if self.gallery.content:
soup_1 = BeautifulSoup(self.gallery.content, 'html.parser')
else:
request_dict = construct_request_dict(self.settings, self.own_settings)
gallery_page = requests.get(
self.gallery.link,
**request_dict
)
soup_1 = BeautifulSoup(gallery_page.content, 'html.parser')
gallery_read = soup_1.find("a", {"class": "x-btn-rounded"})['href']
# Some URLs are really bad formatted
gallery_read = re.sub(
r'.*(' + re.escape(constants.main_page) + r'/manga/read/.+/0/1/).*', r'\1',
gallery_read,
flags=re.DOTALL
)
if not gallery_read or gallery_read in constants.bad_urls or not gallery_read.startswith(constants.main_page):
logger.warning("Reading gallery page not available, trying to guess the name.")
gallery_read = guess_gallery_read_url(self.gallery.link, self.gallery)
if not gallery_read.endswith('page/1'):
gallery_read += 'page/1'
logger.info('Downloading gallery: {}'.format(self.gallery.title))
try:
request_dict = construct_request_dict(self.settings, self.own_settings)
gallery_read_page = requests.get(
gallery_read,
**request_dict
)
except requests.exceptions.MissingSchema:
logger.error("Malformed URL: {}, skipping".format(gallery_read))
self.return_code = 0
return
if gallery_read_page.status_code != 200:
gallery_read = guess_gallery_read_url(self.gallery.link, self.gallery, False)
try:
request_dict = construct_request_dict(self.settings, self.own_settings)
gallery_read_page = requests.get(
gallery_read,
**request_dict
)
except requests.exceptions.MissingSchema:
logger.error("Malformed URL: {}, skipping".format(gallery_read))
self.return_code = 0
return
if gallery_read_page.status_code == 200:
image_urls = self.get_img_urls_from_gallery_read_page(gallery_read_page.text)
if not image_urls:
logger.error("Could not find image links, archive not downloaded")
self.return_code = 0
return
directory_path = mkdtemp()
for image_url in image_urls:
img_name = os.path.basename(image_url)
request_dict = construct_request_dict(self.settings, self.own_settings)
request_file = requests.get(
image_url,
**request_dict
)
if request_file.status_code == 404:
logger.warning("Image link reported 404 error, stopping")
break
with open(os.path.join(directory_path, img_name), "wb") as fo:
for chunk in request_file.iter_content(4096):
fo.write(chunk)
file_path = os.path.join(
self.settings.MEDIA_ROOT,
self.gallery.filename
)
with ZipFile(file_path, 'w') as archive:
for (root_path, _, file_names) in os.walk(directory_path):
for current_file in file_names:
archive.write(
os.path.join(root_path, current_file), arcname=os.path.basename(current_file))
shutil.rmtree(directory_path, ignore_errors=True)
self.gallery.filesize, self.gallery.filecount = get_zip_fileinfo(file_path)
if self.gallery.filesize > 0:
self.crc32 = calc_crc32(file_path)
self.fileDownloaded = 1
self.return_code = 1
else:
logger.error("Wrong HTML code returned, could not download, link: {}".format(gallery_read))
self.return_code = 0