green-spider/checks/generator.py

96 lines
3.2 KiB
Python
Raw Normal View History

"""
Checks the 'generator' meta tag and page content properties
to detect well-known content management systems, themes etc.
"""
from checks.abstract_checker import AbstractChecker
class Checker(AbstractChecker):
# IP address of the newthinking GCMS server
gcms_ip = "91.102.13.20"
def __init__(self, config, previous_results=None):
super().__init__(config, previous_results)
def depends_on_results(self):
return ['page_content', 'html_head', 'dns_resolution']
def run(self):
assert 'page_content' in self.previous_results
assert 'html_head' in self.previous_results
assert 'dns_resolution' in self.previous_results
results = {}
for url in self.config.urls:
results[url] = self.get_generator(url)
return results
def get_generator(self, url):
page_content = self.previous_results['page_content'][url]
assert 'content' in page_content
dns_resolution = self.previous_results['dns_resolution']
head = self.previous_results['html_head'][url]
generator = None
if 'generator' in head and head['generator'] is not None:
generator = head['generator'].lower()
if 'typo3' in generator:
generator = 'typo3'
if 'wordpress' in generator:
generator = 'wordpress'
if 'drupal' in generator:
generator = 'drupal'
if 'joomla' in generator:
generator = 'joomla'
2018-11-05 22:32:06 +01:00
if 'drupal' in generator:
generator = 'drupal'
# Qualify certain CMS flavours in more detail
if generator == "typo3":
# Typo3-Gruene advertises in the page content
if 'typo3-gruene.de' in page_content['content']:
generator = "typo3-gruene"
# newthinking GCMS in some page hrefs
elif 'ntc_gcms' in page_content['content']:
generator = "typo3-gcms"
# check if one of the IPs matches the well-known GCMS Server IP
elif url in dns_resolution:
for addr in dns_resolution[url]['ipv4_addresses']:
if addr == self.gcms_ip:
2018-11-05 23:00:01 +01:00
generator = 'typo3-gcms'
2018-11-28 22:02:30 +01:00
elif 'blum-o-matic' in page_content['content']:
generator = 'wordpress-blumomatic'
elif 'gruenes-internet.de' in page_content['content']:
generator = 'wordpress-gruenes-internet'
elif ('Urwahl3000' in page_content['content'] or
'/themes/urwahl3000' in page_content['content']):
2018-11-05 23:00:01 +01:00
generator = 'wordpress-urwahl'
Job-Verwaltung mit RQ, und vieles mehr (#149) * CLI: remove 'jobs' command, add 'manager' * Add job definition * Move jobs to manage folder * Rename jobs to manager * Add rq and redis dependencies * Add docker-compose YAML * Downgrade to alpine 3.8 * Adjust paths in Dockerfile, remove entrypoint * Rename 'make spiderjobs' to 'make jobs' * Fix docker exectution * Adapt 'make jobs' * Fix metadata scheme * Add docker dependency * Rendomize queue (a bit) * Use latest image, remove debug output * Make docker-compose file downwards-compatible * Use latest instead of dev image tag * Update docker-compose.yaml * Adapt job start script * Fix redis connection in manager * Add support for increasing timeout via environment variable * Adapt load_in_browser to cookies table schema change * Fix execution * Mitigate yaml warning * Bump some dependency versions * Report resource usage stats for each job * checks/load_in_browser: Return DOM size, prevent multiple page loads * Update .dockerignore * Code update * Script update * Update README.md * WIP * WIP commit * Update Dockerfile to alpine:edge and chromium v90 * Update TestCertificateChecker * Set defaults for __init__ function * Detect sunflower theme * Update unit test for new datetime (zero-basing) * Set logging prefs from Chromium in a new way * Move datastore client instantiation As it is not needed for all commands * Change green-directory repository URL * Add git settings for cloning green-directory * Pin alpine version 3.14, fix py3-cryptography * Use plain docker build progress output * Add volumes to 'make test' docker run command * Fix bug * Update example command in README * Update dependencies * Add creation of Kubernetes jobs
2021-11-11 20:15:43 +01:00
elif ('/themes/sunflower' in page_content['content']):
generator = 'wordpress-sunflower'
2021-06-29 21:17:11 +02:00
elif ('/themes/sunflower' in page_content['content']):
generator = 'wordpress-sunflower'
elif ('josephknowsbest' in page_content['content'] or
'Joseph-knows-best' in page_content['content']):
2018-11-05 23:00:01 +01:00
generator = 'wordpress-josephknowsbest'
elif 'wordpress' in page_content['content']:
2018-11-05 23:00:01 +01:00
generator = 'wordpress'
elif 'jimdo' in page_content['content']:
generator = 'jimdo'
return generator