mirror of
https://github.com/netzbegruenung/green-spider.git
synced 2024-05-02 17:14:51 +02:00
Merge pull request #45 from netzbegruenung/pull-icons
Site-Icons herunter laden und als Teil der Webapp hosten
This commit is contained in:
commit
54ac84175d
6
Makefile
6
Makefile
|
@ -9,7 +9,10 @@ dockerimage:
|
|||
|
||||
# Run spider in docker image
|
||||
spider: dockerimage
|
||||
docker run --rm -ti -v $(PWD)/webapp/dist/data:/out spider
|
||||
docker run --rm -ti \
|
||||
-v $(PWD)/webapp/dist/data:/out \
|
||||
-v $(PWD)/docs/siteicons:/icons \
|
||||
spider
|
||||
|
||||
test: dockerimage
|
||||
docker run --rm -ti spider /spider_test.py
|
||||
|
@ -24,7 +27,6 @@ webapp/node_modules:
|
|||
# Build webapp
|
||||
webapp: webapp/node_modules
|
||||
cd webapp && npx webpack --config webpack.config.js
|
||||
rm -rf ./docs/*
|
||||
cp -r webapp/dist/* ./docs/
|
||||
|
||||
serve-webapp:
|
||||
|
|
67
spider.py
67
spider.py
|
@ -8,6 +8,7 @@ from socket import gethostbyname_ex
|
|||
from urllib.parse import urljoin
|
||||
from urllib.parse import urlparse
|
||||
import certifi
|
||||
import hashlib
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
|
@ -34,11 +35,13 @@ read_timeout = 10
|
|||
# Git repo for our data
|
||||
green_directory_repo = 'https://github.com/netzbegruenung/green-directory.git'
|
||||
# folder in that repo that holds the data
|
||||
green_direcory_data_path = 'data/countries/de'
|
||||
green_direcory_data_path = 'data/countries/de/bb'
|
||||
green_directory_local_path = './cache/green-directory'
|
||||
|
||||
result_path = '/out'
|
||||
|
||||
siteicons_path = '/icons'
|
||||
|
||||
# IP address of the newthinking GCMS server
|
||||
gcms_ip = "91.102.13.20"
|
||||
|
||||
|
@ -60,7 +63,7 @@ def dir_entries():
|
|||
Iterator over all data files in the cloned green directory
|
||||
"""
|
||||
path = os.path.join(green_directory_local_path, green_direcory_data_path)
|
||||
for root, dirs, files in os.walk(path):
|
||||
for root, _, files in os.walk(path):
|
||||
for fname in files:
|
||||
|
||||
filepath = os.path.join(root, fname)
|
||||
|
@ -133,6 +136,49 @@ def normalize_title(s):
|
|||
s = s.strip()
|
||||
return s
|
||||
|
||||
def download_icon(icon_url):
|
||||
"""
|
||||
Download an icon from the given URL and store it with
|
||||
a file name of <hash>.<ending>
|
||||
"""
|
||||
|
||||
default_endings = {
|
||||
"image/x-icon": "ico",
|
||||
"image/vnd.microsoft.icon": "ico",
|
||||
"image/png": "png",
|
||||
"image/jpeg": "jpg",
|
||||
}
|
||||
|
||||
# Download the icon
|
||||
r = requests.get(icon_url)
|
||||
r.raise_for_status()
|
||||
|
||||
content_hash = hashlib.md5(r.content).hexdigest()
|
||||
extension = ""
|
||||
|
||||
file_name = os.path.basename(icon_url)[-1]
|
||||
if file_name != "" and "." in file_name:
|
||||
ext = file_name.split(".")[-1]
|
||||
if ext != "":
|
||||
extension = ext
|
||||
|
||||
if extension == "":
|
||||
# derive from content type
|
||||
t = r.headers.get('content-type')
|
||||
try:
|
||||
extension = default_endings[t]
|
||||
except KeyError:
|
||||
logging.error("No file ending defined for icon type '%s'" % t)
|
||||
return None
|
||||
|
||||
filename = content_hash + "." + extension.lower()
|
||||
|
||||
path = siteicons_path + os.path.sep + filename
|
||||
with open(path, 'wb') as iconfile:
|
||||
iconfile.write(r.content)
|
||||
|
||||
return filename
|
||||
|
||||
def check_responsiveness(url):
|
||||
"""
|
||||
Checks
|
||||
|
@ -425,12 +471,12 @@ def check_site(entry):
|
|||
except requests.exceptions.ConnectionError as e:
|
||||
logging.error(str(e) + " " + check_url)
|
||||
check['error'] = "connection"
|
||||
except requests.exceptions.Timeout as e:
|
||||
logging.error(str(e) + " " + check_url)
|
||||
check['error'] = "connection_timeout"
|
||||
except requests.exceptions.ReadTimeout as e:
|
||||
logging.error(str(e) + " " + check_url)
|
||||
check['error'] = "read_timeout"
|
||||
except requests.exceptions.Timeout as e:
|
||||
logging.error(str(e) + " " + check_url)
|
||||
check['error'] = "connection_timeout"
|
||||
except Exception as e:
|
||||
logging.error(str(e) + " " + check_url)
|
||||
check['error'] = "unknown"
|
||||
|
@ -450,7 +496,14 @@ def check_site(entry):
|
|||
continue
|
||||
if c['content']['icon'] is not None:
|
||||
icons.add(c['content']['icon'])
|
||||
result['details']['icons'] = sorted(list(icons))
|
||||
downloaded_icons = set()
|
||||
for icon_url in icons:
|
||||
logging.info("Getting icon %s" % icon_url)
|
||||
try:
|
||||
downloaded_icons.add(download_icon(icon_url))
|
||||
except Exception as e:
|
||||
logging.error("Could not download icon: %s" % e)
|
||||
result['details']['icons'] = sorted(list(downloaded_icons))
|
||||
|
||||
# collect feeds
|
||||
feeds = set()
|
||||
|
@ -630,7 +683,7 @@ def main():
|
|||
"district": entry.get("district"),
|
||||
"city": entry.get("city"),
|
||||
})
|
||||
except NameError as ne:
|
||||
except NameError:
|
||||
logging.error("Error in %s: 'url' key missing (%s)" % (repr_entry(entry), entry['urls'][n]))
|
||||
|
||||
|
||||
|
|
2
webapp/dist/bundle.js
vendored
2
webapp/dist/bundle.js
vendored
File diff suppressed because one or more lines are too long
|
@ -66,7 +66,8 @@ $(function(){
|
|||
|
||||
// FAVICON
|
||||
var icon = item.result.FAVICON.value;
|
||||
row.append('<td class="' + (icon ? 'good' : 'bad') + ' text-center">' + (icon ? ('<img src="' + item.details.icons[0] + '" class="icon">') : '❌') + '</td>');
|
||||
var iconFile = (icon ? item.details.icons[0] : '');
|
||||
row.append('<td class="' + (icon ? 'good' : 'bad') + ' text-center" data-order="'+ iconFile +'">' + (icon ? ('<img src="/siteicons/' + iconFile + '" class="icon" title="'+ iconFile +'">') : '❌') + '</td>');
|
||||
|
||||
// HTTPS
|
||||
var hasHTTPS = item.result.HTTPS.value;
|
||||
|
|
Loading…
Reference in a new issue