def job(self) -> None:
while not self.stop.is_set():
seconds_to_wait = self.wait_until_next_run()
if self.stop.wait(timeout=seconds_to_wait):
return
if self.settings.autoupdater.enable:
current_settings = Settings(load_from_config=self.settings.config)
current_settings.keep_dl_type = True
current_settings.silent_processing = True
current_settings.config['allowed']['replace_metadata'] = 'yes'
connection.close()
start_date = django_tz.now() - timedelta(seconds=int(self.timer)) - timedelta(days=self.settings.autoupdater.buffer_back)
end_date = django_tz.now() - timedelta(days=self.settings.autoupdater.buffer_after)
to_update_providers = current_settings.autoupdater.providers
galleries = Gallery.objects.eligible_for_use(
posted__gte=start_date,
posted__lte=end_date,
provider__in=to_update_providers
)
if not galleries:
logger.info(
"No galleries posted from {} to {} need updating. Providers: {}".format(
start_date,
end_date,
", ".join(to_update_providers)
)
)
else:
# Leave only info downloaders, then leave only enabled auto updated providers
downloaders = current_settings.provider_context.get_downloaders_name_priority(current_settings, filter_name='info')
downloaders_names = [x[0] for x in downloaders if x[0].replace("_info", "") in to_update_providers]
current_settings.allow_downloaders_only(downloaders_names, True, True, True)
url_list = [x.get_link() for x in galleries]
logger.info(
"Starting timed auto updater, updating {} galleries "
"posted from {} to {}. Providers: {}".format(
len(url_list),
start_date,
end_date,
", ".join(to_update_providers)
)
)
url_list.append('--update-mode')
self.web_queue.enqueue_args_list(url_list, override_options=current_settings)
self.update_last_run(django_tz.now())
def process_downloaded_archive(self, archive: Archive) -> None:
if os.path.isfile(archive.zipped.path):
except_at_open = False
return_error = None
try:
my_zip = ZipFile(
archive.zipped.path, 'r')
return_error = my_zip.testzip()
my_zip.close()
except (BadZipFile, NotImplementedError):
except_at_open = True
if except_at_open or return_error:
if 'panda' in archive.source_type:
self.logger.error(
"For archive: {}, file check on downloaded zipfile failed on file: {}, "
"forcing download as panda_archive to fix it.".format(archive, archive.zipped.path)
)
crc32 = calc_crc32(
archive.zipped.path)
Archive.objects.add_or_update_from_values({'crc32': crc32}, pk=archive.pk)
if self.web_queue and archive.gallery:
temp_settings = Settings(load_from_config=self.settings.config)
temp_settings.allow_downloaders_only(['panda_archive'], True, True, True)
self.web_queue.enqueue_args_list((archive.gallery.get_link(),), override_options=temp_settings)
return
else:
self.logger.warning(
"For archive: {}, File check on downloaded zipfile: {}. "
"Check the file manually.".format(archive, archive.zipped.path)
)
crc32 = calc_crc32(
archive.zipped.path)
filesize = get_zip_filesize(
archive.zipped.path)
filecount = filecount_in_zip(
archive.zipped.path)
values = {'crc32': crc32,
'filesize': filesize,
'filecount': filecount,
}
updated_archive = Archive.objects.add_or_update_from_values(
values, pk=archive.pk)
if archive.gallery and updated_archive.filesize != updated_archive.gallery.filesize:
if Archive.objects.filter(gallery=updated_archive.gallery, filesize=updated_archive.gallery.filesize):
self.logger.info(
"For archive: {} size does not match gallery, "
"but there's already another archive that matches.".format(updated_archive)
)
return
if 'panda' in archive.source_type:
self.logger.info(
"For archive: {} size does not match gallery, "
"downloading again from panda_archive.".format(updated_archive)
)
if self.web_queue:
temp_settings = Settings(load_from_config=self.settings.config)
temp_settings.allow_downloaders_only(['panda_archive'], True, True, True)
self.web_queue.enqueue_args_list(
(updated_archive.gallery.get_link(), ),
override_options=temp_settings
)
else:
self.logger.warning(
"For archive: {} size does not match gallery. Check the file manually.".format(archive)
)
def json_parser(request: HttpRequest) -> HttpResponse:
response = {}
if request.method == 'POST':
if not request.body:
response['error'] = 'Empty request'
return HttpResponse(json.dumps(response), content_type="application/json; charset=utf-8")
data = json.loads(request.body.decode("utf-8"))
if 'api_key' not in data:
response['error'] = 'Missing API key'
return HttpResponse(json.dumps(response), content_type="application/json; charset=utf-8")
elif data['api_key'] != crawler_settings.api_key:
response['error'] = 'Incorrect API key'
return HttpResponse(json.dumps(response), content_type="application/json; charset=utf-8")
# send some 'ok' back
else:
if 'operation' not in data or 'args' not in data:
response['error'] = 'Wrong format'
else:
args = data['args']
response = {}
# Used by internal pages and userscript
if data['operation'] == 'webcrawler' and 'link' in args:
if not crawler_settings.workers.web_queue:
response['error'] = 'The webqueue is not running'
elif 'downloader' in args:
current_settings = Settings(load_from_config=crawler_settings.config)
if not current_settings.workers.web_queue:
response['error'] = 'The webqueue is not running'
else:
current_settings.allow_downloaders_only([args['downloader']], True, True, True)
archive = None
parsers = current_settings.provider_context.get_parsers(current_settings, crawler_logger)
for parser in parsers:
if parser.id_from_url_implemented():
urls_filtered = parser.filter_accepted_urls((args['link'], ))
for url_filtered in urls_filtered:
gallery_gid = parser.id_from_url(url_filtered)
if gallery_gid:
archive = Archive.objects.filter(gallery__gid=gallery_gid).first()
if urls_filtered:
break
current_settings.workers.web_queue.enqueue_args_list((args['link'],), override_options=current_settings)
if archive:
response['message'] = "Archive exists, crawling to check for redownload: " + args['link']
else:
response['message'] = "Crawling: " + args['link']
else:
if 'parentLink' in args:
parent_archive = None
parsers = crawler_settings.provider_context.get_parsers(crawler_settings, crawler_logger)
for parser in parsers:
if parser.id_from_url_implemented():
urls_filtered = parser.filter_accepted_urls((args['parentLink'],))
for url_filtered in urls_filtered:
gallery_gid = parser.id_from_url(url_filtered)
if gallery_gid:
parent_archive = Archive.objects.filter(gallery__gid=gallery_gid).first()
if urls_filtered:
break
if parent_archive:
link = parent_archive.gallery.get_link()
if 'action' in args and args['action'] == 'replaceFound':
parent_archive.gallery.mark_as_deleted()
parent_archive.gallery = None
parent_archive.delete_all_files()
parent_archive.delete_files_but_archive()
parent_archive.delete()
response['message'] = "Crawling: " + args['link'] + ", deleting parent: " + link
crawler_settings.workers.web_queue.enqueue_args(args['link'])
elif 'action' in args and args['action'] == 'queueFound':
response['message'] = "Crawling: " + args['link'] + ", keeping parent: " + link
crawler_settings.workers.web_queue.enqueue_args(args['link'])
else:
response['message'] = "Please confirm deletion of parent: " + link
response['action'] = 'confirmDeletion'
else:
archive = None
parsers = crawler_settings.provider_context.get_parsers(crawler_settings, crawler_logger)
for parser in parsers:
if parser.id_from_url_implemented():
urls_filtered = parser.filter_accepted_urls((args['link'],))
for url_filtered in urls_filtered:
gallery_gid = parser.id_from_url(url_filtered)
if gallery_gid:
archive = Archive.objects.filter(gallery__gid=gallery_gid).first()
if urls_filtered:
break
if archive:
response['message'] = "Archive exists, crawling to check for redownload: " + args['link']
else:
response['message'] = "Crawling: " + args['link']
crawler_settings.workers.web_queue.enqueue_args(args['link'])
else:
archive = None
parsers = crawler_settings.provider_context.get_parsers(crawler_settings, crawler_logger)
for parser in parsers:
if parser.id_from_url_implemented():
urls_filtered = parser.filter_accepted_urls((args['link'],))
for url_filtered in urls_filtered:
gallery_gid = parser.id_from_url(url_filtered)
if gallery_gid:
archive = Archive.objects.filter(gallery__gid=gallery_gid).first()
if urls_filtered:
break
if archive:
response['message'] = "Archive exists, crawling to check for redownload: " + args['link']
else:
response['message'] = "Crawling: " + args['link']
crawler_settings.workers.web_queue.enqueue_args(args['link'])
if not response:
response['error'] = 'Could not parse request'
return HttpResponse(json.dumps(response), content_type="application/json; charset=utf-8")
# Used by remotesite command
elif data['operation'] == 'archive_request':
archives_query = Archive.objects.filter_non_existent(crawler_settings.MEDIA_ROOT, gallery__gid__in=args)
archives = [{'gid': archive.gallery.gid,
'id': archive.id,
'zipped': archive.zipped.name,
'filesize': archive.filesize} for archive in archives_query]
response_text = json.dumps({'result': archives})
return HttpResponse(response_text, content_type="application/json; charset=utf-8")
# Used by remotesite command
elif data['operation'] in ('queue_archives', 'queue_galleries'):
urls = args
new_urls_set = set()
gids_set = set()
parsers = crawler_settings.provider_context.get_parsers(crawler_settings, crawler_logger)
for parser in parsers:
if parser.id_from_url_implemented():
urls_filtered = parser.filter_accepted_urls(urls)
for url in urls_filtered:
gid = parser.id_from_url(url)
gids_set.add(gid)
gids_list = list(gids_set)
existing_galleries = Gallery.objects.filter(gid__in=gids_list)
for gallery_object in existing_galleries:
if gallery_object.is_submitted():
gallery_object.delete()
# Delete queue galleries that failed, and does not have archives.
elif data['operation'] == 'queue_archives' and "failed" in gallery_object.dl_type and not gallery_object.archive_set.all():
gallery_object.delete()
elif data['operation'] == 'queue_archives' and not gallery_object.archive_set.all():
gallery_object.delete()
already_present_gids = list(Gallery.objects.filter(gid__in=gids_list).values_list('gid', flat=True))
# new_gids = list(gids_set - set(already_present_gids))
for parser in parsers:
if parser.id_from_url_implemented():
urls_filtered = parser.filter_accepted_urls(urls)
for url in urls_filtered:
gid = parser.id_from_url(url)
if gid not in already_present_gids:
new_urls_set.add(url)
pages_links = list(new_urls_set)
if len(pages_links) > 0:
current_settings = Settings(load_from_config=crawler_settings.config)
if data['operation'] == 'queue_galleries':
current_settings.allow_type_downloaders_only('info')
elif data['operation'] == 'queue_archives':
if 'archive_reason' in data:
current_settings.archive_reason = data['archive_reason']
if 'archive_details' in data:
current_settings.archive_details = data['archive_details']
current_settings.allow_type_downloaders_only('fake')
if current_settings.workers.web_queue:
current_settings.workers.web_queue.enqueue_args_list(pages_links, override_options=current_settings)
else:
pages_links = []
return HttpResponse(json.dumps({'result': str(len(pages_links))}), content_type="application/json; charset=utf-8")
# Used by remotesite command
elif data['operation'] == 'links':
links = args
if len(links) > 0:
crawler_settings.workers.web_queue.enqueue_args_list(links)
return HttpResponse(json.dumps({'result': str(len(links))}), content_type="application/json; charset=utf-8")
# Used by archive page
elif data['operation'] == 'match_archive':
archive = Archive.objects.filter(pk=args['archive'])
if archive:
generate_possible_matches_for_archives(
archive,
filters=(args['match_filter'],),
logger=crawler_logger,
match_local=False,
match_web=True,
)
return HttpResponse(json.dumps({'message': 'web matcher done, check the logs for results'}),
content_type="application/json; charset=utf-8")
elif data['operation'] == 'match_archive_internally':
archive = Archive.objects.get(pk=args['archive'])
if archive:
clear_title = True if 'clear' in args else False
provider_filter = args.get('provider', '')
try:
cutoff = float(request.GET.get('cutoff', '0.4'))
except ValueError:
cutoff = 0.4
try:
max_matches = int(request.GET.get('max-matches', '10'))
except ValueError:
max_matches = 10
archive.generate_possible_matches(
clear_title=clear_title, provider_filter=provider_filter,
cutoff=cutoff, max_matches=max_matches
)
archive.save()
return HttpResponse(json.dumps({'message': 'internal matcher done, check the archive for results'}),
content_type="application/json; charset=utf-8")
else:
response['error'] = 'Unknown function'
elif request.method == 'GET':
data = request.GET
if 'api_key' not in data:
response['error'] = 'Missing API key'
return HttpResponse(json.dumps(response), content_type="application/json; charset=utf-8")
elif data['api_key'] != crawler_settings.api_key:
response['error'] = 'Incorrect API key'
return HttpResponse(json.dumps(response), content_type="application/json; charset=utf-8")
# send some 'ok' back
else:
if 'gc' in data:
args = data.copy()
for k in gallery_filter_keys:
if k not in args:
args[k] = ''
keys = ("sort", "asc_desc")
for k in keys:
if k not in args:
args[k] = ''
# args = data
# Already authorized by api key.
args['public'] = False
results = filter_galleries_no_request(args)
if not results:
return HttpResponse(json.dumps([]), content_type="application/json; charset=utf-8")
response_text = json.dumps(
[{
'gid': gallery.gid,
'token': gallery.token,
'title': gallery.title,
'title_jpn': gallery.title_jpn,
'category': gallery.category,
'uploader': gallery.uploader,
'comment': gallery.comment,
'posted': int(timestamp_or_zero(gallery.posted)),
'filecount': gallery.filecount,
'filesize': gallery.filesize,
'expunged': gallery.expunged,
'rating': gallery.rating,
'hidden': gallery.hidden,
'fjord': gallery.fjord,
'public': gallery.public,
'provider': gallery.provider,
'dl_type': gallery.dl_type,
'tags': gallery.tag_list(),
'link': gallery.get_link(),
'thumbnail': request.build_absolute_uri(reverse('viewer:gallery-thumb', args=(gallery.pk,))) if gallery.thumbnail else '',
'thumbnail_url': gallery.thumbnail_url
} for gallery in results
],
# indent=2,
sort_keys=True,
ensure_ascii=False,
)
return HttpResponse(response_text, content_type="application/json; charset=utf-8")
else:
response['error'] = 'Unknown function'
else:
response['error'] = 'Unsupported method: {}'.format(request.method)
return HttpResponse(json.dumps(response), content_type="application/json; charset=utf-8")
