def test_wrapping_parentheses():
assert linkify('(example.com/)') \
== '(<a href="http://example.com/">example.com/</a>)'
assert linkify('example.com/hi_(there)') \
== '<a href="http://example.com/hi_(there)">example.com/hi_(there)</a>'
assert linkify('(example.com/hi_(there))') \
== '(<a href="http://example.com/hi_(there)">example.com/hi_(there)</a>)'
def test_wrapping_parentheses():
assert linkify('(example.com/)') \
== '(<a href="http://example.com/">example.com/</a>)'
assert linkify('example.com/hi_(there)') \
== '<a href="http://example.com/hi_(there)">example.com/hi_(there)</a>'
assert linkify('(example.com/hi_(there))') \
== '(<a href="http://example.com/hi_(there)">example.com/hi_(there)</a>)'
def test_simple():
assert linkify('a http://example.com link') \
== 'a <a href="http://example.com">http://example.com</a> link'
assert linkify('a https://ya.ru link') \
== 'a <a href="https://ya.ru">https://ya.ru</a> link'
assert linkify('a example.com link') \
== 'a <a href="http://example.com">example.com</a> link'
def test_simple():
assert linkify('a http://example.com link') \
== 'a <a href="http://example.com">http://example.com</a> link'
assert linkify('a https://ya.ru link') \
== 'a <a href="https://ya.ru">https://ya.ru</a> link'
assert linkify('a example.com link') \
== 'a <a href="http://example.com">example.com</a> link'
def get_html(cell):
text = get_text(cell)
spans = cell.get('textFormatRuns', [])
eff = cell.get('effectiveFormat', {'textFormat': {}})['textFormat']
if spans:
fmt = {**eff, **spans[0]['format']}
out = build_tags(fmt)
spans = spans[1:]
previdx = 0
while spans:
out += text[previdx:spans[0]['startIndex']]
previdx = spans[0]['startIndex']
out += build_tags(fmt, True)
fmt = {**eff, **spans[0]['format']}
out += build_tags(fmt)
spans = spans[1:]
out += text[previdx:]
out += build_tags(fmt, True)
else:
out = build_tags(eff)
out += text
out += build_tags(eff, True)
out = out.replace("\n", "<br/>")
out = linkify(out)
return out
def URL_rep(text):
url_info = dict()
extractor = URLExtract()
urls = extractor.find_urls(text)
if not urls:
return url_info
count = 0
for url in urls:
url_org = url
try:
article = Article(url)
response = requests.get(url, verify=False, timeout=20)
if response.status_code != 200:
raise Exception('---------')
except:
temp_url = re.search('"(.*)"', linkify(url)).group(1)
url = temp_url
response = requests.get(url, verify=False, timeout=20)
if response.status_code != 200:
count += 1
url_info[url_org] = "NA"
continue
try:
article = Article(url)
article.download()
article.parse()
title = "\n" + article.title + "\n" + article.text
if not any(item
for item in vaccine_terms if item in title.casefold()):
title = 'NA'
url_info[url_org] = title
except Exception as e:
html = response.content
soup = BeautifulSoup(html, "html.parser") #features="lxml"
matches = soup.findAll(['p', 'title'], text=True,
limit=None) #text = re.compile('vaccin')
linkcontent = []
for node in matches:
if type(node) is bs4.element.Tag:
linkcontent.append(node.get_text())
else:
linkcontent.append(node)
if not linkcontent:
title = 'NA'
elif not any(item for item in vaccine_terms
if item in " ".join(linkcontent).casefold()):
title = 'NA'
else:
title = "\n" + " ".join(linkcontent)
url_info[url_org] = title
return url_info
def process_input_from_rich_text_editor(rich_text):
parsed = rich_text.strip()
exclude_from_parse = {}
now = time.time()
for index, match in enumerate(re.findall('<a [^>]*>.*?</a>', parsed)):
placeholder = f'placeholder-{now}-{index}'
exclude_from_parse[placeholder] = match
parsed = parsed.replace(match, placeholder, 1)
parsed = linkify(parsed, {'target': '_blank'})
for placeholder, match in exclude_from_parse.items():
parsed = parsed.replace(placeholder, match, 1)
return parsed
def render_item(item):
id, type, timestamp, user_id, content, media_path = item
if type == 4:
return ''
inner = ''
id_class = ''
if user_id:
id_class = ' %s' % user_id
inner += '<div class="avatar"></div>\n'
inner += '<div class="container" id="item-%s">\n' % id
if content:
inner += '<div class="content">%s</div>\n' % linkify(content)
if media_path:
media_path = media_path.replace('output/', '')
media = ''
if type == 2:
media = '<a href="%s"><img src="%s" /></a>\n' % (media_path,
media_path)
elif type == 3:
media = '<audio controls><source src="%s" type="audio/mpeg"></audio>\n' % media_path
inner += '<div class="media">%s</div>\n' % media
if timestamp:
time = datetime.fromtimestamp(timestamp).strftime('%c')
inner += '<div class="timestamp"><a href="#item-%s">%s</a></div>\n' % (
id, time)
inner += '</div>\n'
return '<div class="item%s">\n%s</div>\n' % (id_class, inner)
def test_uppercase():
assert linkify('HTTP://EXAMPLE.COM') \
== '<a href="HTTP://EXAMPLE.COM">HTTP://EXAMPLE.COM</a>'
def add_links(s):
return linkify(s)
def test_attrs():
assert linkify('ya.ru', attrs={'rel': 'nofollow'}) \
== '<a href="http://ya.ru" rel="nofollow">ya.ru</a>'
def test_nonascii():
assert linkify(u'http://\u5350.net/') \
== u'<a href="http://\u5350.net/">http://\u5350.net/</a>'
def test_query():
assert linkify('xx.com/?a=hi&b=bye') \
== '<a href="http://xx.com/?a=hi&b=bye">xx.com/?a=hi&b=bye</a>'
wrapper = TextWrapper(
break_long_words=False,
break_on_hyphens=False,
width=80
)
wrapped = ''
for line in content.splitlines():
prefix = ''
matches = re.match('^\s+', line)
if matches:
prefix = matches.group(0)
wrapped += ('\n' + prefix).join(wrapper.wrap(line)) + '\n'
content = autolink.linkify(wrapped)
# Because autolink is buggy
content = content.replace("http://(http://", "http://")
content = content.replace(")\">", "\">")
# This looks weird, because it is. This is to deal with overlapping patterns.
oldcontent = False
while oldcontent != content:
oldcontent = content
content = re.sub(
"(^|[ (])@([a-zA-Z0-9_]+)([. )]|$)",
"\\1<a href='https://twitter.com/\\2'>@\\2</a>\\3",
content,
flags=re.M
)
def test_query():
assert linkify('xx.com/?a=hi&b=bye') \
== '<a href="http://xx.com/?a=hi&b=bye">xx.com/?a=hi&b=bye</a>'
def test_port():
assert linkify('foo.com:8000') \
== '<a href="http://foo.com:8000">foo.com:8000</a>'
assert linkify('foo.com:xkcd') \
== '<a href="http://foo.com">foo.com</a>:xkcd'
def test_bad_protocols():
assert linkify('foohttp://bar') == 'foohttp://bar'
assert linkify('fohttp://exampl.com') \
== 'fohttp://<a href="http://exampl.com">exampl.com</a>'
def test_non_domain():
assert linkify('ha.ha') == 'ha.ha'
def test_fragment():
assert linkify('http://xx.com/path#frag') \
== '<a href="http://xx.com/path#frag">http://xx.com/path#frag</a>'
def test_complete():
assert linkify('https://*****:*****@ftp.mozilla.org/x/y.exe?a=b&c=d&e#f') \
== '<a href="https://*****:*****@ftp.mozilla.org/x/y.exe?a=b&c=d&e#f">' \
'https://*****:*****@ftp.mozilla.org/x/y.exe?a=b&c=d&e#f</a>'
def test_port():
assert linkify('foo.com:8000') \
== '<a href="http://foo.com:8000">foo.com:8000</a>'
assert linkify('foo.com:xkcd') \
== '<a href="http://foo.com">foo.com</a>:xkcd'
def test_fragment():
assert linkify('http://xx.com/path#frag') \
== '<a href="http://xx.com/path#frag">http://xx.com/path#frag</a>'
def test_punct():
assert linkify('http://example.com.') \
== '<a href="http://example.com">http://example.com</a>.'
assert linkify('http://example.com,') \
== '<a href="http://example.com">http://example.com</a>,'
def test_complete():
assert linkify('https://*****:*****@ftp.mozilla.org/x/y.exe?a=b&c=d&e#f') \
== '<a href="https://*****:*****@ftp.mozilla.org/x/y.exe?a=b&c=d&e#f">' \
'https://*****:*****@ftp.mozilla.org/x/y.exe?a=b&c=d&e#f</a>'
def test_bad_protocols():
assert linkify('foohttp://bar') == 'foohttp://bar'
assert linkify('fohttp://exampl.com') \
== 'fohttp://<a href="http://exampl.com">exampl.com</a>'
def test_non_domain():
assert linkify('ha.ha') == 'ha.ha'
def test_punct():
assert linkify('http://example.com.') \
== '<a href="http://example.com">http://example.com</a>.'
assert linkify('http://example.com,') \
== '<a href="http://example.com">http://example.com</a>,'
def test_uppercase():
assert linkify('HTTP://EXAMPLE.COM') \
== '<a href="HTTP://EXAMPLE.COM">HTTP://EXAMPLE.COM</a>'
def test_attrs():
assert linkify('ya.ru', attrs={'rel': 'nofollow'}) \
== '<a href="http://ya.ru" rel="nofollow">ya.ru</a>'
def test_email():
assert linkify('mailto:[email protected]') \
== '<a href="mailto:[email protected]">mailto:[email protected]</a>'
assert linkify('*****@*****.**') \
== '<a href="mailto:[email protected]">[email protected]</a>'
def test_nonascii():
assert linkify(u'http://\u5350.net/') \
== u'<a href="http://\u5350.net/">http://\u5350.net/</a>'
def test_email():
assert linkify('mailto:[email protected]') \
== '<a href="mailto:[email protected]">mailto:[email protected]</a>'
assert linkify('*****@*****.**') \
== '<a href="mailto:[email protected]">[email protected]</a>'
def test_nested_email():
assert linkify('http://[email protected]') \
== '<a href="http://[email protected]">' \
'http://[email protected]</a>'
def test_nested_email():
assert linkify('http://[email protected]') \
== '<a href="http://[email protected]">' \
'http://[email protected]</a>'
def html_body(self):
return Markup(linkify(escape(self.body)))
import jinja2, os
from jinja2 import utils
import datetime
from autolink import linkify
import cgi
def day_of_date(date):
""" a filter to convert dates into strings suitable for display on the day-of page"""
offset = datetime.timedelta(hours=-5)
return (date + offset).strftime('%A, %I:%M %p')
JINJA_ENVIRONMENT = jinja2.Environment(
loader=jinja2.FileSystemLoader(os.path.join(os.path.dirname(__file__), 'templates')),
extensions=['jinja2.ext.autoescape'],
autoescape=True)
JINJA_ENVIRONMENT.filters['day_of_date'] = day_of_date
JINJA_ENVIRONMENT.filters['linkify'] = lambda text: linkify(cgi.escape(text))
def template(filename, vals={}):
return JINJA_ENVIRONMENT.get_template(filename).render(vals)
def template_string(template, vals={}):
return jinja2.Template(template).render(vals)
import jinja2, os
from jinja2 import utils
import datetime
from autolink import linkify
import cgi
def day_of_date(date):
""" a filter to convert dates into strings suitable for display on the day-of page"""
offset = datetime.timedelta(hours=-5)
return (date + offset).strftime('%A, %I:%M %p')
JINJA_ENVIRONMENT = jinja2.Environment(loader=jinja2.FileSystemLoader(
os.path.join(os.path.dirname(__file__), 'templates')),
extensions=['jinja2.ext.autoescape'],
autoescape=True)
JINJA_ENVIRONMENT.filters['day_of_date'] = day_of_date
JINJA_ENVIRONMENT.filters['linkify'] = lambda text: linkify(cgi.escape(text))
def template(filename, vals={}):
return JINJA_ENVIRONMENT.get_template(filename).render(vals)
def template_string(template, vals={}):
return jinja2.Template(template).render(vals)
