def sanitize_html(content):
"""
Converts content to safe HTML
"""
sanitizer = Sanitizer()
content = sanitizer.sanitize(content)
return content
def parse_opportunity(self, response):
full_payload = ""
# Blurt it all out in full for now.
sanitizer = Sanitizer({
'tags': ('hr', 'a', 'br', 'p', 'ul', 'ol', 'li', 'h1', 'h2', 'h3',
'table', 'tbody', 'tr', 'td'),
})
matches = response.xpath('.//div[@class="column-one-whole"]').extract()
for item in matches:
full_payload = "".join(sanitizer.sanitize(item))
self.store_opportunity({
'title':
response.css('header h1::text').extract_first().strip(),
'url':
response.request.url,
'incomplete_applications':
response.css('#incomplete-applications .big-statistic::text'
).extract_first().strip(),
'complete_applications':
response.css('#completed-applications .big-statistic::text').
extract_first().strip(),
'full_text':
full_payload,
})
def edit_profile(request):
user = get_object_or_404(get_user_model(), pk=request.user.pk)
if hasattr(user, 'userprofile'):
up_instance = user.userprofile
else:
up_instance = None
if request.method == "POST":
user_form = P7UserChangeForm(request.POST,
instance=user,
initial={'confirm_email': user.email})
profile_form = UserProfileForm(request.POST,
request.FILES,
instance=up_instance)
if all([user_form.is_valid(), profile_form.is_valid()]):
user_form.save()
profile = profile_form.save(commit=False)
profile.user = user
sanitizer = Sanitizer()
profile.bio = sanitizer.sanitize(profile.bio)
profile.save()
return redirect(reverse('accounts:profile'))
else: # GET
user_form = P7UserChangeForm(instance=user,
initial={'confirm_email': user.email})
profile_form = UserProfileForm(instance=up_instance)
template = 'accounts/edit_profile.html'
context = {'user_form': user_form, 'profile_form': profile_form}
return render(request, template, context)
def getList():
sanitizer = Sanitizer()
number_list = ""
for file in os.listdir("C:/Bitnami/wampstack-7.3.6-2/apache2/htdocs/data"):
number_list = number_list + "<li><a href = 'index.py?id={name}'>{name}</a></li>".format(
name=file)
number_list = sanitizer.sanitize(number_list)
return number_list
def getList():
sanitizer = Sanitizer()
files = os.listdir('data')
listStr = ''
for item in files:
listStr += '<li><a href="index.py?id={name}">{name}</a></li>'.format(
name=sanitizer.sanitize(item))
return listStr
def do_GET(self):
try:
request_url = urlparse(self.requestline)
all_companies = request_url.query.split(
',') # Get all company names from URL
allJobsXml = ET.Element('jobs')
for i in range(len(all_companies)):
r = requests.get(
f"https://apply.workable.com/api/v1/widget/accounts/{all_companies[i].split()[0]}?details=true"
)
data = r.json()
for job in data["jobs"]:
jobXml = ET.SubElement(allJobsXml, 'job')
titleXml = ET.SubElement(jobXml, 'title')
titleXml.text = job["title"]
employerXml = ET.SubElement(jobXml, 'Email')
employerXml.text = f"team+{all_companies[i].split()[0]}@climate.careers"
urlXml = ET.SubElement(jobXml, 'url')
urlXml.text = job["url"]
locationXml = ET.SubElement(jobXml, 'location')
locationXml.text = job["city"] + ", " + job[
"state"] + ", " + job["country"]
# HTML Sanitizer
sanitizer = Sanitizer({
'tags': ('em', 'strong', 'a', 'p', 'br', 'span', 'ul',
'ol', 'li', 'h1', 'h2', 'h3', 'hr'),
'attributes': {
"a": "href"
},
})
descriptionXml = ET.SubElement(jobXml, 'description')
descriptionXml.text = sanitizer.sanitize(
job["description"])
idXml = ET.SubElement(jobXml, 'id')
idXml.text = job["shortcode"]
self.send_response(200)
self.send_header('Content-type', 'text/xml')
self.send_header(
'Cache-Control',
'public, immutable, no-transform, s-maxage=3600, max-age=3600')
self.end_headers()
message = ET.tostring(allJobsXml)
self.wfile.write(message)
return
except Exception as e:
self.send_response(500)
self.send_header('Content-type', 'text/html')
self.end_headers()
message = f"<h1>Internal Error</h1><p>Sorry, there was a problem. Make sure the employer's name is " \
"included in the URL query and/or is the correct name.</p> "
message2 = f"<p>{e}</p>"
self.wfile.write(message2.encode())
return
def post(self):
"""Update announcement"""
user = self.get_current_user()
sanitizer = Sanitizer()
# announcement = self.get_body_argument("announcement")
announcement = sanitizer.sanitize(
self.get_body_argument("announcement"))
self.queue.update(user["name"], announcement)
self.redirect(self.application.reverse_url("view"))
def get_list():
sanitizer = Sanitizer()
files = os.listdir('data')
str_lst = ''
for item in files:
item = sanitizer.sanitize(item)
str_lst = str_lst + '<li><a href="index.py?id={name}">{name}</a></li>'.format(
name=item)
return str_lst
def handle(event, context):
ddb = boto3.resource('dynamodb')
messages_table = MessagesStore(ddb)
if "getAllMessages" in json.loads(event["body"]):
connections_url = "https://" + event["requestContext"][
"domainName"] + "/" + os.environ["Stage"]
gatewayapi = boto3.client("apigatewaymanagementapi",
endpoint_url=connections_url)
apigateway_response = gatewayapi.post_to_connection(
ConnectionId=event["requestContext"]["connectionId"],
Data=json.dumps(messages_table.get_messages()).encode('utf-8'))
return {"statusCode": 200}
connections_table = ConnectionsStore(ddb)
data = {"connectionId": event["requestContext"]["connectionId"]}
connections_ids = connections_table.get_connections()
sanitizer = Sanitizer()
chat_message = sanitizer.sanitize(json.loads(event["body"])["data"])
lambda_client = boto3.client('lambda')
analysis_handler_function_name = "{}-{}".format(os.environ["Stage"],
"AnalysisHandler")
response = lambda_client.invoke(
FunctionName=analysis_handler_function_name,
InvocationType='RequestResponse',
Payload=json.dumps({"message": chat_message}))
sentiment_response = response['Payload'].read().decode("utf-8")
messageToSend = {
"action": "sendMessage",
"data": {
"message": chat_message,
"sentiment": sentiment_response
}
}
message_data_for_ddb = {
"date": date.today().strftime("%d-%m-%Y"),
"timestamp": int(round(time.time() * 1000)),
"message": messageToSend["data"]
}
messages_table.add_new_message(**message_data_for_ddb)
for connection_id in connections_ids:
connections_url = "https://" + event["requestContext"][
"domainName"] + "/" + os.environ["Stage"]
gatewayapi = boto3.client("apigatewaymanagementapi",
endpoint_url=connections_url)
apigateway_response = gatewayapi.post_to_connection(
ConnectionId=connection_id['connectionId'],
Data=json.dumps(messageToSend).encode('utf-8'))
return {"statusCode": 200}
def process_item(self, item, spider):
if spider.name != 'these_people':
return item
sanitizer = sanitizer = Sanitizer({
'empty': {
'h1', 'h2', 'h3', 'strong', 'em', 'p', 'ul', 'ol', 'li', 'br',
'sub', 'sup', 'hr', 'a'
},
'separate': set()
})
if (item['languages'][0] == 'Sprachkenntnisse:'):
item['languages'] = item['languages'][1:]
if (item['education'][0] == 'Abschluss:'):
item['education'] = item['education'][1:]
if (item['hourly_daily_rate'][0] == 'Stunden-/Tagessatz:'):
item['hourly_daily_rate'] = item['hourly_daily_rate'][1:]
h_d_rate = ' '.join(item['hourly_daily_rate'])
h_d_rate = re.sub(' +|\n', '|', h_d_rate).split('|')
item['hourly_daily_rate'] = list(
filter(None, [i.strip() for i in h_d_rate if i]))
item['languages'] = ''.join(item['languages']).split('|')
item['skills'] = sanitizer.sanitize(''.join(item['skills']))
item['other_info'] = sanitizer.sanitize(''.join(item['other_info']))
item['availability'] = sanitizer.sanitize(''.join(
item['availability']))
return item
def clean_webpage(cls, item):
if item is None:
return item, None, None
with open(item, "r", encoding="utf-8") as input_f:
html = input_f.read()
soup = BeautifulSoup(html, "lxml")
cls.bs4_aggressive_remove(soup)
sanitized = Sanitizer(settings=config.sanitizer_settings).sanitize(
str(soup))
fresh_soup = BeautifulSoup(sanitized, "lxml")
sanitized_policy = os.path.abspath(
os.path.join(config.processed_policies, os.path.basename(item)))
with open(sanitized_policy, "w", encoding="utf-8") as output_f:
output_f.write(f"<html>\n"
f"<head>\n"
f"\t<meta charset=\"utf-8\"/>\n"
f"\t<title></title>\n"
f"</head>\n"
f"{cls.prettify(fresh_soup.body)}\n"
f"</html>")
return item, sanitized_policy
def _compose_html(self, tagged_text, hard_words):
sanitizer = Sanitizer({
'tags': {'p', 'mark', 'span'},
'attributes': {
'span': ('class', )
},
'empty': set(),
'separate': {'p', 'mark', 'span'},
})
html_paragraphs = []
for paragraph in tagged_text.iter('chunk'):
sentences = []
for sentence in paragraph.iter('sentence'):
no_space = False
s = ''
for pos, el in enumerate(sentence):
if el.tag == 'ns':
no_space = True
continue
elif el.tag == 'tok':
orth = el.xpath('orth/text()')[0]
base = el.xpath('lex/base/text()')[0]
if orth in hard_words or base in hard_words:
orth = '<mark>{}</mark>'.format(orth)
if no_space:
s += orth
no_space = False
else:
s += ' ' + orth
sentence_length = sentence.xpath('count(./tok)')
if sentence_length > 20:
self.long_sentence_count += 1
s = '<span class="long_sentence">{}</span>'.format(s)
sentences.append(s)
html_paragraphs.append('<p>{}</p>'.format(' '.join(sentences)))
html_text = ''.join(html_paragraphs)
return sanitizer.sanitize(html_text)
def get_content(url):
try:
web_page = requests.get(url, allow_redirects=True, timeout=5)
except requests.exceptions.Timeout as err:
raise ServerException(
description=
"Failed to fetch web page in time! Skipping preprocessing")
soup = BeautifulSoup(web_page.content, "html.parser")
content = str(soup.section)
try:
for field in soup.find('ul', attrs={"class": "details"}).children:
field_str = str(field)
field_str = field_str.replace("\n", "")
print(field_str)
if "#icon-contract" in field_str:
m = findall(r"svg>(\w|\s)+<\/li>", field_str)
# print(field.string)
sanitiser = Sanitizer()
content = sanitiser.sanitize(content)
return {"post_details": content, "fields": {}}
except:
raise InvalidUserInput(
description="Couldn't find details for that job")
def _decode_data_url(cls, url):
"""Convert a data: URL to a string of sanitized HTML.
:raise ValueError: If the data: URL is invalid, in an
unexpected format, or does not have a supported media type.
:return: A string.
"""
if not url.startswith("data:"):
raise ValueError("Not a data: URL: %s" % url)
parts = url.split(",")
if len(parts) != 2:
raise ValueError("Invalid data: URL: %s" % url)
header, encoded = parts
if not header.endswith(";base64"):
raise ValueError("data: URL not base64-encoded: %s" % url)
media_type = header[len("data:"):-len(";base64")]
if not any(
media_type.startswith(x) for x in ("text/html", "text/plain")):
raise ValueError("Unsupported media type in data: URL: %s" %
media_type)
html = base64.b64decode(encoded)
return Sanitizer().sanitize(html)
CONF_DICT['gui_chat']['style_settings'] = LCStaticBox()
CONF_DICT['gui_chat']['style_settings']['show_system_msg'] = LCBool(True)
CONF_DICT['gui_chat']['style_settings']['show_history'] = LCBool(True)
CONF_DICT['server_chat'] = LCPanel()
CONF_DICT['server_chat']['style'] = LCChooseSingle(DEFAULT_STYLE,
check_type='dir',
folder='http',
empty_label=True)
CONF_DICT['server_chat']['style_settings'] = LCStaticBox()
CONF_DICT['server_chat']['style_settings']['show_system_msg'] = LCBool(True)
CONF_DICT['server_chat']['style_settings']['show_history'] = LCBool(True)
TYPE_DICT = {TextMessage: 'message', CommandMessage: 'command'}
SANITIZER = Sanitizer()
def process_emotes(emotes):
return [{
'id': EMOTE_FORMAT.format(emote.id),
'url': emote.url
} for emote in emotes]
def process_badges(badges):
return [{'badge': badge.id, 'url': badge.url} for badge in badges]
def process_platform(platform):
return {'id': platform.id, 'icon': platform.icon}
def update_temp():
# Get local cottage temp
f = open('/sys/bus/w1/devices/28-000007171178/w1_slave', 'r')
cot = f.readline()
if "YES" not in cot:
raise Exception("Bad CRC for Cottage temp sensor")
cot = f.readline()
cot = cot.split("t=")
cot = cot[1].rstrip("\n")
cot = temp_to_format_str(float(cot)/1000)
f.close()
# Get local cottage temp and humidity from DHT
f = open('/sys/bus/iio/devices/iio:device0/in_temp_input', 'r')
success = False
tries = 0
while not(success):
try:
cot2 = temp_to_format_str(float(f.readline())/1000)
success = True
except OSError as e:
tries = tries + 1
if tries > 10:
cot2 = "ERR"
break
f.close()
f = open('/sys/bus/iio/devices/iio:device0/in_humidityrelative_input', 'r')
success = False
tries = 0
while not(success):
try:
hm = str(round(float(f.readline())/1000,2)) + " %"
success = True
except OSError as e:
tries = tries + 1
if tries > 10:
hm = "ERR"
break
f.close()
tempCottage.set(cot)
tempCottage2.set(cot2)
humid.set(hm)
# Get info from pumphouse
r = requests.get("http://192.168.0.180/temp")
# Set encoding to UTF-8 since the HTML is in it but apparently the ESP sends a different one
r.encoding = "UTF-8"
# Throw error if applicable
if not(r.ok):
lakeTempVar = "ERR"
outsideTempVar = "ERR"
intakeTempVar = "ERR"
ambientTempVar = "ERR"
else:
# Clean up and split response
sanitizer = Sanitizer()
txt = sanitizer.sanitize(r.text)
# Split on line breaks and remove all but temp info
txtSplit = txt.split("<br>")[1:5]
for item in txtSplit:
tempS = item.split(":")
tmpValue = float(removeNonDecimal(tempS[1]))
if "Lake" == tempS[0]:
lakeTempVar = temp_to_format_str(tmpValue)
elif "Outside" == tempS[0]:
outsideTempVar = temp_to_format_str(tmpValue)
elif "Pump intake" == tempS[0]:
intakeTempVar = temp_to_format_str(tmpValue)
elif "Ambient outdoor" == tempS[0]:
ambientTempVar = temp_to_format_str(tmpValue)
tempLake.set(lakeTempVar)
tempOutside.set(outsideTempVar)
tempIntake.set(intakeTempVar)
tempAmb.set(ambientTempVar)
csvwriter.writerow({'Time': time.strftime("%F %T"), 'Outside Temp': removeNonDecimal(outsideTempVar), 'Cottage Temp': removeNonDecimal(cot), 'Cottage Temp (DHT)': removeNonDecimal(cot2), 'Lake Temp': removeNonDecimal(lakeTempVar), 'Pump Intake': removeNonDecimal(intakeTempVar), 'Ambient Lake Temp': removeNonDecimal(ambientTempVar), 'Humidity': removeNonDecimal(hm)})
from airflow.models import Variable
from airflow.hooks.postgres_hook import PostgresHook
from html_sanitizer import Sanitizer
import nltk
from utilities import safeget
from rock_media import is_media_video, is_media_audio
import requests
nltk.download('punkt')
summary_sanitizer = Sanitizer({
'tags': {'h1', 'h2', 'h3', 'h4', 'h5', 'h6'},
'empty': {},
'separate': {},
'attributes': {},
})
html_allowed_tags = {
'h1',
'h2',
'h3',
'h4',
'h5',
'h6',
'blockquote',
'p',
'a',
'ul',
'ol',
from django.shortcuts import render, redirect
import random
from main.forms import AdModelForm, FiltersForm
from main.models import User, Ad, Skill, PetProject, Responsibility, Pide
from djmoney.money import Money
from html_sanitizer import Sanitizer
sanitizer = Sanitizer()
sanitizer.tags = set(sanitizer.tags).union([
'p', 'span', 'i', 'u', 'hr', 'ol', 'li', 'br', 'blockquote', 'ul', 'pre',
'h1', 'h2', 'h3', 'h4', 'h5', 'h6'
])
##################################################
# Helper functions
##################################################
def negate_ad(ad_type):
assert (ad_type == "vacancy" or ad_type == "resume")
return 'vacancy' if ad_type == 'resume' else 'resume'
def save_skills(post, ad):
i = 1
last = post.get('skill1')
while last is not None:
Skill.objects.create(text=last, ad_id=ad).save()
from django.shortcuts import render, redirect, get_object_or_404
from django.http import Http404, HttpResponse
from django.conf import settings
from django.core.exceptions import PermissionDenied, ValidationError
from django.contrib.auth.mixins import LoginRequiredMixin
from django.contrib.admin.views.decorators import staff_member_required
from django.views.generic.list import ListView
from .models import Video, Audio, VideoPlaylist, AudioPlaylist, Text, Upload, SiteSetting
import uuid
from .panopto import panopto_oauth2
from html_sanitizer import Sanitizer
html_sanitizer = Sanitizer()
html = html_sanitizer.sanitize
def shib_bounce(request):
"""This view is for bouncing the user to the desired location after they
have authenticated with Shibboleth and been bounced back to /login.
Assumes that a 'next' argument has been set in the URL. E.g.
'/login?next=/inventory/'.
PersistentRemoteUserMiddleware logs the user in automatically, so there is
no need for this view to do this work manually.
"""
try:
next = request.GET['next']
except KeyError:
raise Http404("No bounce destination.")
if request.user.is_authenticated:
return redirect(next)
else:
import sys
import traceback
from flask import Flask, request, render_template, send_from_directory, Response
import validators
from util.validate import validate_email
from util.validate import validate_phone
from util.db import db
from html_sanitizer import Sanitizer
import time
import util.env
from util.mail import send_email
from requests import get, post
from os import environ
sanitizer = Sanitizer()
app = Flask(__name__)
app.secret_key = 'Zli6WMDUEboJnp34fzwK'.encode('utf8')
@app.route('/assets/<path>')
def send_assets(path):
return send_from_directory('assets', path)
@app.route('/assets/icons/<path>')
def send_icons(path):
return send_from_directory('assets/icons', path)
from html_sanitizer import Sanitizer
# import the logging library
import logging
# Get an instance of a logger
logger = logging.getLogger(__name__)
# Limit results for ElasticSearch to this number by Default
ES_DEFAULT_LIMIT = 50
sanitizer = Sanitizer({
'tags': {'a',},
'attributes': {
'a': ('href', 'name', 'target', 'title', 'id'),
},
'empty': set(),
'separate': {'a',},
})
class EmailController():
"""
Email utility controller, sends emails based on templates
"""
# Get an instance of a logger
logger = logging.getLogger("EmailController")
sender = u'OffenesParlament <*****@*****.**>'
fail_silently = False
sanitizer = Sanitizer({
'tags': (
'a',
'b',
'blockquote',
'br',
'center',
'code',
'del',
'em',
'h1',
'h2',
'h3',
'h4',
'h5',
'h6',
'hr',
'img',
'i',
'li',
'ol',
'pre',
'p',
'strike',
'strong',
'sup',
'sub',
'ul',
),
'attributes': {
"a": ("href", "name", "title", "id", "rel"),
"img": ("src", "width", "height", "alt"),
},
'element_preprocessors': [],
'sanitize_href':
sanitize_href,
})
# CATEGORY_STRING = "Grace Hopper"
# MANIFEST_URL = "http://example.com"
CATEGORY_STRING = sys.argv[1]
MANIFEST_URL = sys.argv[2]
COMMONS_CAT_TEMPLATE = u"https://commons.wikimedia.org/w/api.php?action=query&\
generator=categorymembers&iiurlwidth={0}&gcmtitle=\
Category:{1}&gcmlimit=500&gcmtype=file&prop=imageinfo&\
iiprop=url|timestamp|user|mime|extmetadata&format=json"
HEADERS = {'user-agent': 'Science Stories API ([email protected])'}
sanitizer = Sanitizer({
'tags': {'a', 'b', 'br', 'i', 'img', 'p', 'span'},
'attributes': {
'a': ('href'),
'img': ('src', 'alt')
},
'empty': {'br'},
'separate': {'a', 'p'}
})
html_converter = HTML2Text()
html_converter.ignore_links = True
def main():
"""Call Main Function."""
return iiif_cat_manifest(CATEGORY_STRING)
def safe_str(obj):
"""Return unicode encoding."""
f.write(full_html)
for a in articles:
app_body = ''
print(f"Process {a['url']}...")
article = json.loads(
subprocess.getoutput(f"../api/read-article {a['url']}"))
article['url'] = a['url']
article['body'] = markdown.markdown(article['body'],
extensions=md_extensions,
output_format='html5')
article['body'] = update_link(article['body'], a['url'])
article['comments_body'] = ''
for comment in article.get('comments', {}):
sanitizer = Sanitizer()
comment['body'] = markdown.markdown(comment['body'],
extensions=md_extensions,
output_format='html5')
comment['body'] = sanitizer.sanitize(comment['body'])
if comment['site']:
if comment['site'].startswith(
'https://') or comment['site'].startswith('http://'):
comment['site'] = sanitizer.sanitize(comment['site'])
else:
comment['site'] = None
article['comments_body'] += comment_tpl(comment)
app_body += article_tpl(article)
full_html = main_tpl({
'body': app_body,
#!C:\Users\msy94\AppData\Local\Programs\Python\Python37\python.exe
#!python3
#-*- coding: utf-8 -*-
import sys, codecs, os
sys.stdout = codecs.getwriter("utf-8")(sys.stdout.detach())
import cgi, cgitb
import view
cgitb.enable()
print("Content-Type: text/html; charset=utf-8\r\n")
print()
form = cgi.FieldStorage()
from html_sanitizer import Sanitizer
sanitizer = Sanitizer()
if "id" in form:
title = pageId = form["id"].value
description = open("data/"+pageId, encoding="utf-8").read()
description = sanitizer.sanitize(description)
title = sanitizer.sanitize(title)
update_link = "<a href = 'update.py?id={pageId}'>update</a>".format(pageId = pageId)
delete_action = '''
<form action="process_delete.py" method="post">
<input type = "hidden" name = "pageId" value="{}">
<input type = "submit" value = "delete">
</form>
'''.format(pageId)
else:
title = pageId = "Welcome"
description = "Hello Web"
update_link = ""
delete_action = ""
print(pageId)
sanitizer = Sanitizer({
"tags": {
"a",
"b",
"blockquote",
"br",
"div",
"em",
"h1",
"h2",
"h3",
"hr",
"i",
"li",
"ol",
"p",
"span",
"strong",
"sub",
"sup",
"ul",
"img",
},
"attributes": {
"a": ("href", "name", "target", "title", "id", "rel", "src", "style")
},
"empty": {"hr", "a", "br", "div"},
"separate": {"a", "p", "li", "div"},
"whitespace": {"br"},
"keep_typographic_whitespace": False,
"add_nofollow": False,
"autolink": False,
})
