CIRCL
/
AIL-framework
mirror of https://github.com/CIRCL/AIL-framework
2
1
Fork 0
Code Issues Releases Wiki Activity

chg: [crawler] manual/auto crawler: always save screenshots

pull/350/head
Terrtia 2019-05-13 14:24:16 +02:00
parent 254441f193
commit 0389b9c23b
No known key found for this signature in database
GPG Key ID: 1E1B1F50D84613D0
2 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
bin/torcrawler/TorSplashCrawler.py
View File

@ -48,16 +48,16 @@ class TorSplashCrawler():
'DEPTH_LIMIT': crawler_options['depth_limit'] 'DEPTH_LIMIT': crawler_options['depth_limit']
}) })
def crawl(self, type, crawler_options, date, url, domain, port, original_item): def crawl(self, type, crawler_options, date, requested_mode, url, domain, port, original_item):
self.process.crawl(self.crawler, type=type, crawler_options=crawler_options, date=date, url=url, domain=domain, port=port, original_item=original_item) self.process.crawl(self.crawler, type=type, crawler_options=crawler_options, date=date, requested_mode=requested_mode, url=url, domain=domain, port=port, original_item=original_item)
self.process.start() self.process.start()
class TorSplashSpider(Spider): class TorSplashSpider(Spider):
name = 'TorSplashSpider' name = 'TorSplashSpider'
def __init__(self, type, crawler_options, date, url, domain, port, original_item, *args, **kwargs): def __init__(self, type, crawler_options, date, requested_mode, url, domain, port, original_item, *args, **kwargs):
self.type = type self.type = type
self.requested = crawler_options['requested'] self.requested_mode = requested_mode
self.original_item = original_item self.original_item = original_item
self.root_key = None self.root_key = None
self.start_urls = url self.start_urls = url
@ -184,7 +184,7 @@ class TorSplashCrawler():
if 'png' in response.data: if 'png' in response.data:
size_screenshot = (len(response.data['png'])*3) /4 size_screenshot = (len(response.data['png'])*3) /4
if size_screenshot < 5000000 or self.requested: #bytes or manual/auto if size_screenshot < 5000000 or self.requested_mode: #bytes or manual/auto
image_content = base64.standard_b64decode(response.data['png'].encode()) image_content = base64.standard_b64decode(response.data['png'].encode())
hash = sha256(image_content).hexdigest() hash = sha256(image_content).hexdigest()
img_dir_path = os.path.join(hash[0:2], hash[2:4], hash[4:6], hash[6:8], hash[8:10], hash[10:12]) img_dir_path = os.path.join(hash[0:2], hash[2:4], hash[4:6], hash[6:8], hash[8:10], hash[10:12])

3
bin/torcrawler/tor_crawler.py
View File

@ -43,8 +43,9 @@ if __name__ == '__main__':
original_item = crawler_json['item'] original_item = crawler_json['item']
crawler_options = crawler_json['crawler_options'] crawler_options = crawler_json['crawler_options']
date = crawler_json['date'] date = crawler_json['date']
requested_mode = crawler_json['requested']
redis_cache.delete('crawler_request:{}'.format(uuid)) redis_cache.delete('crawler_request:{}'.format(uuid))
crawler = TorSplashCrawler(splash_url, crawler_options) crawler = TorSplashCrawler(splash_url, crawler_options)
crawler.crawl(service_type, crawler_options, date, url, domain, port, original_item) crawler.crawl(service_type, crawler_options, date, requested_mode, url, domain, port, original_item)