def test_smart_urlquote(self):
items = (
("http://öäü.com/", "http://xn--4ca9at.com/"),
("http://öäü.com/öäü/",
"http://xn--4ca9at.com/%C3%B6%C3%A4%C3%BC/"),
# Everything unsafe is quoted, !*'();:@&=+$,/?#[]~ is considered
# safe as per RFC.
(
"http://example.com/path/öäü/",
"http://example.com/path/%C3%B6%C3%A4%C3%BC/",
),
("http://example.com/%C3%B6/ä/",
"http://example.com/%C3%B6/%C3%A4/"),
("http://example.com/?x=1&y=2+3&z=",
"http://example.com/?x=1&y=2+3&z="),
("http://example.com/?x=<>\"'",
"http://example.com/?x=%3C%3E%22%27"),
(
"http://example.com/?q=http://example.com/?x=1%26q=django",
"http://example.com/?q=http%3A%2F%2Fexample.com%2F%3Fx%3D1%26q%3D"
"django",
),
(
"http://example.com/?q=http%3A%2F%2Fexample.com%2F%3Fx%3D1%26q%3D"
"django",
"http://example.com/?q=http%3A%2F%2Fexample.com%2F%3Fx%3D1%26q%3D"
"django",
),
("http://.www.f oo.bar/", "http://.www.f%20oo.bar/"),
)
# IDNs are properly quoted
for value, output in items:
with self.subTest(value=value, output=output):
self.assertEqual(smart_urlquote(value), output)
def clean_content_url(url, content_type):
"""
埋め込みタイプのコンテンツのURLをcleanする
- remove_query_string: `?`以降のクエリストリングを削除
- remove_hash_string: `#`以降のハッシュストリングを削除
- remove_last_slash: URLの最後の`/`を削除
"""
def remove_query_string(url):
splitted_url = url.split("?")
if len(splitted_url) > 1:
url = splitted_url[0]
return url
def remove_hash_string(url):
splitted_url = url.split("#")
if len(splitted_url) > 1:
url = splitted_url[0]
return url
def remove_last_slash(url):
if url[-1] == "/":
url = url[:-1]
return url
if not url:
return url
# URLエンコーディング
url = smart_urlquote(url)
# 埋め込みタイプなら、不要な文字列を削除(WEBの場合は不要)
if content_type in EMBED_TYPES and content_type != WEB:
url = remove_query_string(url)
url = remove_hash_string(url)
url = remove_last_slash(url)
return url
def gravatar_for_email(email, size=None, rating=None):
"""
Generates a Gravatar URL for the given email address.
Syntax::
{% gravatar_for_email <email> [size] [rating] %}
Example::
{% gravatar_for_email [email protected] 48 pg %}
"""
gravatar_url = "%savatar/%s" % (GRAVATAR_URL_PREFIX,
_get_gravatar_id(email))
parameters = [p for p in (
('d', GRAVATAR_DEFAULT_IMAGE),
('s', size or GRAVATAR_DEFAULT_SIZE),
('r', rating or GRAVATAR_DEFAULT_RATING),
) if p[1]]
if parameters:
gravatar_url += '?' + urllib.urlencode(parameters, doseq=True)
return smart_urlquote(gravatar_url)
def get_context(self, name, value, attrs):
context = super().get_context(name, value, attrs)
context['current_label'] = _('Currently:')
context['change_label'] = _('Change:')
context['widget']['href'] = smart_urlquote(
context['widget']['value']) if value else ''
return context
def get_context(self, name, value, attrs):
context = super().get_context(name, value, attrs)
context["current_label"] = _("Currently:")
context["change_label"] = _("Change:")
context["widget"]["href"] = (smart_urlquote(context["widget"]["value"])
if value else "")
return context
def test_smart_urlquote(self):
items = (
('http://öäü.com/', 'http://xn--4ca9at.com/'),
('http://öäü.com/öäü/',
'http://xn--4ca9at.com/%C3%B6%C3%A4%C3%BC/'),
# Everything unsafe is quoted, !*'();:@&=+$,/?#[]~ is considered
# safe as per RFC.
('http://example.com/path/öäü/',
'http://example.com/path/%C3%B6%C3%A4%C3%BC/'),
('http://example.com/%C3%B6/ä/',
'http://example.com/%C3%B6/%C3%A4/'),
('http://example.com/?x=1&y=2+3&z=',
'http://example.com/?x=1&y=2+3&z='),
('http://example.com/?x=<>"\'',
'http://example.com/?x=%3C%3E%22%27'),
('http://example.com/?q=http://example.com/?x=1%26q=django',
'http://example.com/?q=http%3A%2F%2Fexample.com%2F%3Fx%3D1%26q%3Ddjango'
),
('http://example.com/?q=http%3A%2F%2Fexample.com%2F%3Fx%3D1%26q%3Ddjango',
'http://example.com/?q=http%3A%2F%2Fexample.com%2F%3Fx%3D1%26q%3Ddjango'
),
)
# IDNs are properly quoted
for value, output in items:
with self.subTest(value=value, output=output):
self.assertEqual(smart_urlquote(value), output)
def urlize_quoted_hrefs(text, trim_url_limit=None, nofollow=True, autoescape=True):
"""
Converts href in text into clickable links. If trim_url_limit is not None, the URLs in link
text longer than this limit will truncated to trim_url_limit-3 characters and appended with
an ellipsis. If nofollow is True, the URLs in link text will get a rel="nofollow" attribute.
"""
def trim_url(x, limit=trim_url_limit):
return limit is not None and (len(x) > limit and ('%s...' % x[:max(0, limit - 3)])) or x
safe_input = isinstance(text, SafeData)
words = word_split_re.split(force_text(text))
for i, word in enumerate(words):
if '/pulp/api/v3/' in word:
# Deal with punctuation.
lead, middle, trail = '', word, ''
for punctuation in TRAILING_PUNCTUATION:
if middle.endswith(punctuation):
middle = middle[:-len(punctuation)]
trail = punctuation + trail
for opening, closing in WRAPPING_PUNCTUATION:
if middle.startswith(opening):
middle = middle[len(opening):]
lead = lead + opening
# Keep parentheses at the end only if they're balanced.
if middle.endswith(closing) and \
middle.count(closing) == middle.count(opening) + 1:
middle = middle[:-len(closing)]
trail = closing + trail
# Make URL we want to point to.
url = None
nofollow_attr = ' rel="nofollow"' if nofollow else ''
if href_re.match(middle):
url = smart_urlquote(middle)
# Check if it's a real URL
if url and ("{" in url or "%7B" in url):
url = None
# Make link.
if url:
trimmed = trim_url(middle)
if autoescape and not safe_input:
lead, trail = escape(lead), escape(trail)
url, trimmed = escape(url), escape(trimmed)
middle = '<a href="%s"%s>%s</a>' % (url, nofollow_attr, trimmed)
words[i] = mark_safe('%s%s%s' % (lead, middle, trail))
else:
if safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
elif safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
return ''.join(words)
def append(value):
if value:
output = '<a href="{href}" class="add-on" target="_blank"><i class="icon-globe"></i></a>'
href = force_str(value)
return format_html(output, href=smart_urlquote(href))
else:
output = '<span class="add-on"><i class="icon-globe"></i></span>'
return format_html(output)
def get_unityroom_embed_html(self):
# プロジェクトURLのHTML取得
html = self.get_bs4_html()
# aタグからWebGLのURLを取得
a_tag = html.select_one("div.spec-games-center a[target='_blank']")
safe_webgl_url = smart_urlquote(a_tag.get("href"))
# 埋め込み用のHTMLを生成
embed_html = f'<iframe src="{safe_webgl_url}" width="560" height="358" scrolling="no" frameborder="0" allowfullscreen></iframe>' # noqa: E501
return embed_html
def render(self, name, value, attrs=None):
html = super(AdminURLFieldWidget, self).render(name, value, attrs)
if value:
value = force_text(self._format_value(value))
final_attrs = {'href': mark_safe(smart_urlquote(value))}
html = format_html(
'<p class="url"><a {0} target="_blank">Visit this site</a><br />{1}</p>',
flatatt(final_attrs), html)
return html
def render(self, name, value, attrs=None):
html = super(AdminURLFieldWidget, self).render(name, value, attrs)
if value:
value = force_text(self._format_value(value))
final_attrs = {'href': smart_urlquote(value)}
html = format_html('<p class="url">{} <a{}>{}</a><br />{} {}</p>',
_('Currently:'), flatatt(final_attrs), value,
_('Change:'), html)
return html
def smart_urlquote_wrapper(matched_url):
"""
Simple wrapper for smart_urlquote. ValueError("Invalid IPv6 URL") can
be raised here, see issue #1386
"""
try:
return smart_urlquote(matched_url)
except ValueError:
return None
def render(self, name, value, attrs=None):
html = super(AdminURLFieldWidget, self).render(name, value, attrs)
if value:
value = force_text(self._format_value(value))
final_attrs = {"href": mark_safe(smart_urlquote(value))}
html = format_html(
'<p class="url"><a {0} target="_blank">Visit this site</a><br />{1}</p>', flatatt(final_attrs), html
)
return html
def smart_urlquote_wrapper(matched_url):
"""
Simple wrapper for smart_urlquote. ValueError("Invalid IPv6 URL") can
be raised here, see issue #1386
"""
try:
return smart_urlquote(matched_url)
except ValueError:
return None
def render(self, name, value, attrs=None):
html = super().render(name, value, attrs)
if value:
url = '{}{}'.format(settings.ISSUE_TRACKER_URL, value)
final_attrs = {'href': smart_urlquote(url), 'target': '_blank'}
html = format_html(
'<div class="ticket-url">{}<a{}>{}</a></div>',
html, flatatt(final_attrs), url,
)
return html
def render(self, name, value, attrs=None):
markup = super(widgets.AdminURLFieldWidget, self).render(
name, value, attrs)
if value:
value = force_text(self.format_value(value))
final_attrs = {'href': html.smart_urlquote(value)}
markup = html.format_html(
'<p class="url">{}<br />{} <a{}>{}</a></p>',
markup, _('Currently:'), flatatt(final_attrs), value,
)
return markup
def render(self, name, value, attrs=None):
html = super(AdminURLFieldWidget, self).render(name, value, attrs)
if value:
value = force_text(self._format_value(value))
final_attrs = {'href': mark_safe(smart_urlquote(value))}
html = format_html(
'<p class="url">{0} <a {1}>{2}</a><br />{3} {4}</p>',
_('Currently:'), flatatt(final_attrs), value,
_('Change:'), html
)
return html
def get_context(self, name, value, attrs):
try:
self.validator(value if value else '')
url_valid = True
except ValidationError:
url_valid = False
context = super().get_context(name, value, attrs)
context['current_label'] = _('Currently:')
context['change_label'] = _('Change:')
context['widget']['href'] = smart_urlquote(context['widget']['value']) if value else ''
context['url_valid'] = url_valid
return context
def get_context(self, name, value, attrs):
try:
self.validator(value if value else '')
url_valid = True
except ValidationError:
url_valid = False
context = super().get_context(name, value, attrs)
context['current_label'] = _('Currently:')
context['change_label'] = _('Change:')
context['widget']['href'] = smart_urlquote(context['widget']['value']) if value else ''
context['url_valid'] = url_valid
return context
def render(self, name, value, attrs=None):
if value is None:
return None
final_attrs = self.build_attrs(attrs)
href = smart_urlquote(value)
text = self.text or href
return format_html(
'<a href="{href}" {attrs}>{text}</a>',
href=href,
attrs=flatatt(final_attrs),
text=force_str(text),
)
def get_context(self, name, value, attrs):
try:
self.validator(value if value else '')
url_valid = True
except ValidationError:
url_valid = False
context = super().get_context(name, value, attrs)
context['current_label'] = _('Currently:')
context['change_label'] = _('Change:')
context['url_valid'] = url_valid
if url_valid is True:
http_urls = s3_to_http_schema(value, True)
if http_urls["distributed"] is not None:
context['distributed_label'] = _('Distributed:')
context['distributed_value'] = smart_urlquote(
http_urls["distributed"])
context['widget']['href'] = smart_urlquote(http_urls["pre_signed"])
return context
def parse_url(word):
"""
If word is url, return a parsed version of it.
:param word: string
:return: None or parsed url
"""
url = None
if simple_url_re.match(word):
url = smart_urlquote(word)
elif simple_url_2_re.match(word):
url = smart_urlquote('http://%s' % word)
elif not ':' in word and simple_email_re.match(word):
local, domain = word.rsplit('@', 1)
try:
domain = domain.encode('idna').decode('ascii')
except UnicodeError:
return
url = 'mailto:%s@%s' % (local, domain)
if url:
return urlparse.urlparse(url)
def get_context(self, name, value, attrs):
try:
self.validator(value if value else "")
url_valid = True
except ValidationError:
url_valid = False
context = super().get_context(name, value, attrs)
context["current_label"] = _("Currently:")
context["change_label"] = _("Change:")
context["widget"]["href"] = (smart_urlquote(context["widget"]["value"])
if value else "")
context["url_valid"] = url_valid
return context
def render(self, name, value, attrs=None):
if value:
value = self.get_url(value)
html = super(ForumToolsIDFieldWidget, self).render(name, value, attrs)
if value:
value = force_text(value)
final_attrs = {'href': smart_urlquote(value)}
html = format_html(
'<p class="url">{0} <a{1}>{2}</a><br />{3} {4}</p>',
_('Currently:'), flatatt(final_attrs), value,
_('Change:'), html
)
return html
def parse_url(word):
"""
If word is url, return a parsed version of it.
:param word: string
:return: None or parsed url
"""
url = None
if simple_url_re.match(word):
url = smart_urlquote(word)
elif simple_url_2_re.match(word):
url = smart_urlquote('http://%s' % word)
elif not ':' in word and simple_email_re.match(word):
local, domain = word.rsplit('@', 1)
try:
domain = domain.encode('idna').decode('ascii')
except UnicodeError:
return
url = 'mailto:%s@%s' % (local, domain)
if url:
return urlparse.urlparse(url)
def render(self, name, value, attrs=None):
markup = super(widgets.AdminURLFieldWidget,
self).render(name, value, attrs)
if value:
value = force_text(self.format_value(value))
final_attrs = {'href': html.smart_urlquote(value)}
markup = html.format_html(
'<p class="url">{}<br />{} <a{}>{}</a></p>',
markup,
_('Currently:'),
flatatt(final_attrs),
value,
)
return markup
def render(self, name, value, attrs=None):
html = super(AdminURLFieldWidget, self).render(name, value, attrs)
if value:
value = force_text(self._format_value(value))
final_attrs = {"href": smart_urlquote(value)}
html = format_html(
'<p class="url">{} <a{}>{}</a><br />{} {}</p>',
_("Currently:"),
flatatt(final_attrs),
value,
_("Change:"),
html,
)
return html
def render(self, name, value, attrs=None):
if value is None:
return format_html(
'<p class="text-error">{text}</p>',
text=_('Populate form fields above'),
)
final_attrs = self.build_attrs(attrs)
href = smart_urlquote(value)
text = self.text or href
return format_html(
'<p><a href="{href}" {attrs}>{text}</a></p>',
href=href,
attrs=flatatt(final_attrs),
text=force_str(text),
)
def get_sketchfab_embed_html(self):
# プロジェクトURLのHTML取得
html = self.get_bs4_html()
# プロジェクト投稿ユーザーのSketchfabURL取得
safe_user_link = smart_urlquote(
html.select_one("a.user-name__link").get("href"))
# プロジェクトURLの32文字のID取得
project_id = re.search(r"[a-f0-9]{32}", self.encoded_url).group(0)
iframe_html = 'main/sketchfab_iframe.html'
context = {
"project_id": project_id,
"encoded_url": self.encoded_url,
"user_link": safe_user_link
}
embed_html = render_to_string(iframe_html, context)
return embed_html
def _subpage_crawler(self):
"""Create the list of products by finding the link of each product page"""
while True:
try:
family = self.product_families.pop()
except IndexError:
break
with closing(urlopen(self.base_url + family)) as product_list_page:
product_list_soup = BeautifulSoup(product_list_page,
'html.parser')
product_list = product_list_soup.find_all('table',
bgcolor='#EFEEE4')
for product in product_list:
product_url = product.find('a').get('href')
product_url = '/' + product_url.split('/')[1]
product_url = smart_urlquote(product_url)
self.product_links[product_url] = family
def test_smart_urlquote(self):
items = (
('http://öäü.com/', 'http://xn--4ca9at.com/'),
('http://öäü.com/öäü/', 'http://xn--4ca9at.com/%C3%B6%C3%A4%C3%BC/'),
# Everything unsafe is quoted, !*'();:@&=+$,/?#[]~ is considered
# safe as per RFC.
('http://example.com/path/öäü/', 'http://example.com/path/%C3%B6%C3%A4%C3%BC/'),
('http://example.com/%C3%B6/ä/', 'http://example.com/%C3%B6/%C3%A4/'),
('http://example.com/?x=1&y=2+3&z=', 'http://example.com/?x=1&y=2+3&z='),
('http://example.com/?x=<>"\'', 'http://example.com/?x=%3C%3E%22%27'),
('http://example.com/?q=http://example.com/?x=1%26q=django',
'http://example.com/?q=http%3A%2F%2Fexample.com%2F%3Fx%3D1%26q%3Ddjango'),
('http://example.com/?q=http%3A%2F%2Fexample.com%2F%3Fx%3D1%26q%3Ddjango',
'http://example.com/?q=http%3A%2F%2Fexample.com%2F%3Fx%3D1%26q%3Ddjango'),
)
# IDNs are properly quoted
for value, output in items:
with self.subTest(value=value, output=output):
self.assertEqual(smart_urlquote(value), output)
def get_context(self, name, value, attrs):
context = super(AdminURLFieldWidget, self).get_context(name, value, attrs)
context['current_label'] = _('Currently:')
context['change_label'] = _('Change:')
context['widget']['href'] = smart_urlquote(context['widget']['value']) if value else ''
return context
def _product_crawler(self):
from products.models import Product, Picture, Price
# Return the price in the right format
def _to_decimal(s):
from decimal import Decimal as D
return D(s.strip().replace(u'€', '').replace(',',
'.').replace(' ', ''))
while True:
try:
product_url, category = self.product_links.popitem()
except KeyError:
break
try:
with closing(urlopen(product_url)) as product_page:
product_soup = BeautifulSoup(product_page, 'html.parser')
except HTTPError:
print 'error loading page for object at url', self.base_url + product_url
# Get the image
if product_soup.find('img', class_='alignleft wp-post-image'):
image_url = product_soup.find(
'img', class_='alignleft wp-post-image').get('src')
elif product_soup.find('a', class_='lightbox'):
image_url = product_soup.find('a',
class_='lightbox').get('href')
else:
image_url = 'http://www.axxlocations.fr/wp-content/themes/axxlocations/img/logo.jpg'
image_url = smart_urlquote(image_url)
# Get the title
infosProduits = product_soup.find(
'article', class_=re.compile('post[0-9]*')).find('h1').text
# Get the description
try:
description = product_soup.find('div',
id='produit-avantages').text
except:
description = ''
pass
try:
description += product_soup.find(
'div', id='produits-carateristiques').text
except:
pass
# Format the title
summary = infosProduits
deposit_amount = 0.0
# print 'url:%s \n img:%s \n infos:%s \n description:%s \n summary:%s' % (product_url, image_url, infosProduits, description, summary)
# Create the product
from products.models import Category, Price
from products.choices import UNIT
try:
product = Product.objects.create(
summary=summary,
description=description,
deposit_amount=deposit_amount,
address=self.address,
owner=self.patron,
category=Category.objects.get(
slug=category_mapping[category]))
try:
with closing(urlopen(image_url)) as image:
product.pictures.add(
Picture.objects.create(
image=uploadedfile.SimpleUploadedFile(
name='img', content=image.read())))
except HTTPError as e:
print '\nerror loading image for object at url:', self.base_url + product_url
pass
except:
print 'CANNOT CREATE PRODUCT : %s' % summary
pass
def _wrap_img_tag(url, info, size):
return '<img src="%s"%s alt="Avatar for %s" height="%s" width="%s"/>' % \
(smart_urlquote(url), _imgclass_attr(), info, size, size)
if attrs is not None:
final_attrs.update(attrs)
<<<<<<< HEAD
super(AdminURLFieldWidget, self).__init__(attrs=final_attrs)
def get_context(self, name, value, attrs):
context = super(AdminURLFieldWidget, self).get_context(name, value, attrs)
=======
super().__init__(attrs=final_attrs)
def get_context(self, name, value, attrs):
context = super().get_context(name, value, attrs)
>>>>>>> 37c99181c9a6b95433d60f8c8ef9af5731096435
context['current_label'] = _('Currently:')
context['change_label'] = _('Change:')
context['widget']['href'] = smart_urlquote(context['widget']['value']) if value else ''
return context
class AdminIntegerFieldWidget(forms.NumberInput):
class_name = 'vIntegerField'
def __init__(self, attrs=None):
final_attrs = {'class': self.class_name}
if attrs is not None:
final_attrs.update(attrs)
<<<<<<< HEAD
super(AdminIntegerFieldWidget, self).__init__(attrs=final_attrs)
=======
super().__init__(attrs=final_attrs)
>>>>>>> 37c99181c9a6b95433d60f8c8ef9af5731096435
def test_smart_urlquote(inp):
smart_urlquote(inp)
def get_context(self, name, value, attrs):
context = super(AdminURLFieldWidget, self).get_context(name, value, attrs)
context['current_label'] = _('Currently:')
context['change_label'] = _('Change:')
context['widget']['href'] = smart_urlquote(context['widget']['value'])
return context
def convert_links(text, trim_url_limit=None, nofollow=False, autoescape=False):
"""
Finds URLs in text and attempts to handle correctly.
Heavily based on django.utils.html.urlize
With the additions of attempting to embed media links, particularly images.
Works on http://, https://, www. links, and also on links ending in one of
the original seven gTLDs (.com, .edu, .gov, .int, .mil, .net, and .org).
Links can have trailing punctuation (periods, commas, close-parens) and
leading punctuation (opening parens) and it'll still do the right thing.
TO-DO: refactor to better leverage existing django.utils.html
"""
safe_input = isinstance(text, SafeData)
words = word_split_re.split(force_text(text))
for i, word in enumerate(words):
if '.' in word or ':' in word:
# Deal with punctuation.
lead, middle, trail = '', word, ''
stripped = middle.rstrip(TRAILING_PUNCTUATION_CHARS)
if middle != stripped:
trail = middle[len(stripped):] + trail
middle = stripped
for opening, closing in WRAPPING_PUNCTUATION:
if middle.startswith(opening):
middle = middle[len(opening):]
lead = lead + opening
# Keep parentheses at the end only if they're balanced.
if (middle.endswith(closing)
and middle.count(closing) == middle.count(opening) + 1):
middle = middle[:-len(closing)]
trail = closing + trail
# Make URL we want to point to.
url = None
if simple_url_re.match(middle):
url = smart_urlquote(middle)
elif simple_url_2_re.match(middle):
url = smart_urlquote('http://%s' % middle)
elif ':' not in middle and is_email_simple(middle):
local, domain = middle.rsplit('@', 1)
try:
domain = domain.encode('idna').decode('ascii')
except UnicodeError:
continue
if url:
u = url.lower()
if autoescape and not safe_input:
lead, trail = escape(lead), escape(trail)
url = escape(url)
# Photos
if u.endswith('.jpg') or u.endswith('.gif') or u.endswith('.png'):
middle = '<img src="%s">' % url
# Youtube
#'https://www.youtube.com/watch?v=gkqXgaUuxZg'
elif 'youtube.com/watch' in url:
parsed = urlparse.urlsplit(url)
query = urlparse.parse_qs(parsed.query)
token = query.get('v')
if token and len(token) > 0:
middle = '<iframe src="http://www.youtube.com/embed/%s" height="320" width="100%%"></iframe>' % token[0]
else:
middle = url
elif 'youtu.be/' in url:
try:
token = url.rsplit('/', 1)[1]
middle = '<iframe src="http://www.youtube.com/embed/%s" height="320" width="100%%"></iframe>' % token
except IndexError:
middle = six.u(url)
words[i] = mark_safe('%s%s%s' % (lead, middle, trail))
else:
if safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
elif safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
return ''.join(words)
def get_context(self, name, value, attrs):
context = super().get_context(name, value, attrs)
context['current_label'] = _('Currently:')
context['change_label'] = _('Change:')
context['widget']['href'] = smart_urlquote(context['widget']['value'])
return context
def urlize_quoted_hrefs(text,
trim_url_limit=None,
nofollow=True,
autoescape=True):
"""
Converts href in text into clickable links. If trim_url_limit is not None, the URLs in link
text longer than this limit will truncated to trim_url_limit-3 characters and appended with
an ellipsis. If nofollow is True, the URLs in link text will get a rel="nofollow" attribute.
"""
def trim_url(x, limit=trim_url_limit):
return limit is not None and (len(x) > limit and
('%s...' % x[:max(0, limit - 3)])) or x
safe_input = isinstance(text, SafeData)
words = word_split_re.split(force_text(text))
for i, word in enumerate(words):
if '/pulp/api/v3/' in word:
# Deal with punctuation.
lead, middle, trail = '', word, ''
for punctuation in TRAILING_PUNCTUATION:
if middle.endswith(punctuation):
middle = middle[:-len(punctuation)]
trail = punctuation + trail
for opening, closing in WRAPPING_PUNCTUATION:
if middle.startswith(opening):
middle = middle[len(opening):]
lead = lead + opening
# Keep parentheses at the end only if they're balanced.
if (middle.endswith(closing) and middle.count(closing)
== middle.count(opening) + 1):
middle = middle[:-len(closing)]
trail = closing + trail
# Make URL we want to point to.
url = None
nofollow_attr = ' rel="nofollow"' if nofollow else ''
if href_re.match(middle):
url = smart_urlquote(middle)
# Check if it's a real URL
if url and ("{" in url or "%7B" in url):
url = None
# Make link.
if url:
trimmed = trim_url(middle)
if autoescape and not safe_input:
lead, trail = escape(lead), escape(trail)
url, trimmed = escape(url), escape(trimmed)
middle = '<a href="%s"%s>%s</a>' % (url, nofollow_attr,
trimmed)
words[i] = mark_safe('%s%s%s' % (lead, middle, trail))
else:
if safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
elif safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
return ''.join(words)
"""
def urlize_impl(text, trim_url_limit=None, nofollow=False, autoescape=False):
"""
Converts any URLs in text into clickable links.
Works on http://, https://, www. links, and also on links ending in one of
the original seven gTLDs (.com, .edu, .gov, .int, .mil, .net, and .org).
Links can have trailing punctuation (periods, commas, close-parens) and
leading punctuation (opening parens) and it'll still do the right thing.
If trim_url_limit is not None, the URLs in link text longer than this limit
will truncated to trim_url_limit-3 characters and appended with an elipsis.
If nofollow is True, the URLs in link text will get a rel="nofollow"
attribute.
If autoescape is True, the link text and URLs will get autoescaped.
"""
trim_url = lambda x, limit=trim_url_limit: limit is not None and (len(x) > limit and ('%s...' % x[:max(0, limit - 3)])) or x
safe_input = isinstance(text, SafeData)
words = word_split_re.split(force_text(text))
for i, word in enumerate(words):
match = None
if '.' in word or '@' in word or ':' in word:
# Deal with punctuation.
lead, middle, trail = '', word, ''
for punctuation in TRAILING_PUNCTUATION:
if middle.endswith(punctuation):
middle = middle[:-len(punctuation)]
trail = punctuation + trail
for opening, closing in WRAPPING_PUNCTUATION:
if middle.startswith(opening):
middle = middle[len(opening):]
lead = lead + opening
# Keep parentheses at the end only if they're balanced.
if (middle.endswith(closing)
and middle.count(closing) == middle.count(opening) + 1):
middle = middle[:-len(closing)]
trail = closing + trail
# Make URL we want to point to.
url = None
nofollow_attr = ' rel="nofollow"' if nofollow else ''
if simple_url_re.match(middle):
url = smart_urlquote(middle)
elif simple_url_2_re.match(middle):
url = smart_urlquote('http://%s' % middle)
elif not ':' in middle and simple_email_re.match(middle):
local, domain = middle.rsplit('@', 1)
try:
domain = domain.encode('idna').decode('ascii')
except UnicodeError:
continue
url = 'mailto:%s@%s' % (local, domain)
nofollow_attr = ''
# Make link.
if url:
trimmed = trim_url(middle)
if autoescape and not safe_input:
lead, trail = escape(lead), escape(trail)
url, trimmed = escape(url), escape(trimmed)
#
# Custom stuff for us
#
lowered = url.lower()
is_image = (lowered.endswith('.jpg') or lowered.endswith('.gif')
or lowered.endswith('.png'))
class_attr = is_image and ' class="image"' or ''
middle = '<a href="%s"%s%s>%s</a>' % (url, nofollow_attr,
class_attr, trimmed)
#
# End custom stuff
#
words[i] = mark_safe('%s%s%s' % (lead, middle, trail))
else:
if safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
elif safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
return ''.join(words)
def convert_links(text, trim_url_limit=None, nofollow=False, autoescape=False):
"""
Finds URLs in text and attempts to handle correctly.
Heavily based on django.utils.html.urlize
With the additions of attempting to embed media links, particularly images.
Works on http://, https://, www. links, and also on links ending in one of
the original seven gTLDs (.com, .edu, .gov, .int, .mil, .net, and .org).
Links can have trailing punctuation (periods, commas, close-parens) and
leading punctuation (opening parens) and it'll still do the right thing.
"""
safe_input = isinstance(text, SafeData)
words = word_split_re.split(force_text(text))
for i, word in enumerate(words):
if '.' in word or ':' in word:
# Deal with punctuation.
lead, middle, trail = '', word, ''
for punctuation in TRAILING_PUNCTUATION:
if middle.endswith(punctuation):
middle = middle[:-len(punctuation)]
trail = punctuation + trail
for opening, closing in WRAPPING_PUNCTUATION:
if middle.startswith(opening):
middle = middle[len(opening):]
lead = lead + opening
# Keep parentheses at the end only if they're balanced.
if (middle.endswith(closing)
and middle.count(closing) == middle.count(opening) + 1):
middle = middle[:-len(closing)]
trail = closing + trail
# Make URL we want to point to.
url = None
if simple_url_re.match(middle):
url = smart_urlquote(middle)
elif simple_url_2_re.match(middle):
url = smart_urlquote('http://%s' % middle)
elif not ':' in middle and simple_email_re.match(middle):
local, domain = middle.rsplit('@', 1)
try:
domain = domain.encode('idna').decode('ascii')
except UnicodeError:
continue
if url:
u = url.lower()
if autoescape and not safe_input:
lead, trail = escape(lead), escape(trail)
url = escape(url)
# Photos
if u.endswith('.jpg') or u.endswith('.gif') or u.endswith('.png'):
middle = '<img src="%s">' % url
# Youtube
#'https://www.youtube.com/watch?v=gkqXgaUuxZg'
elif 'youtube.com/watch' in url:
parsed = urlparse.urlsplit(url)
query = urlparse.parse_qs(parsed.query)
token = query.get('v')
if token and len(token) > 0:
middle = '<iframe src="http://www.youtube.com/embed/%s" height="320" width="100%%"></iframe>' % token[0]
else:
middle = url
elif 'youtu.be/' in url:
try:
token = url.rsplit('/', 1)[1]
middle = '<iframe src="http://www.youtube.com/embed/' + token + '" height="320" width="100%%"></iframe>'
except IndexError:
middle = url
words[i] = mark_safe('%s%s%s' % (lead, middle, trail))
else:
if safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
elif safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
return ''.join(words)
def __init__(self, content_type, project_url):
self.type = content_type
# HTMLのhref用
self.encoded_url = smart_urlquote(project_url)
# HTMLのinnerText用
self.safe_url = escape(unquote(project_url))
def _urlize_all_text(text,
trim_url_limit=None,
nofollow=False,
autoescape=False):
"""
Convert any URLs in text into clickable links.
Works on http://, https://, www. links, and also on links ending in one of
the original seven gTLDs (.com, .edu, .gov, .int, .mil, .net, and .org).
Links can have trailing punctuation (periods, commas, close-parens) and
leading punctuation (opening parens) and it'll still do the right thing.
If trim_url_limit is not None, truncate the URLs in the link text longer
than this limit to trim_url_limit - 1 characters and append an ellipsis.
If nofollow is True, give the links a rel="nofollow" attribute.
If autoescape is True, autoescape the link text and URLs.
"""
safe_input = isinstance(text, SafeData)
def trim_url(x, limit=trim_url_limit):
if limit is None or len(x) <= limit:
return x
return '%s…' % x[:max(0, limit - 1)]
def trim_punctuation(lead, middle, trail):
"""
Trim trailing and wrapping punctuation from `middle`. Return the items
of the new state.
"""
# Continue trimming until middle remains unchanged.
trimmed_something = True
while trimmed_something:
trimmed_something = False
# Trim wrapping punctuation.
for opening, closing in WRAPPING_PUNCTUATION:
if middle.startswith(opening):
middle = middle[len(opening):]
lead += opening
trimmed_something = True
# Keep parentheses at the end only if they're balanced.
if middle.endswith(closing) and middle.count(
closing) == middle.count(opening) + 1:
middle = middle[:-len(closing)]
trail = closing + trail
trimmed_something = True
# Trim trailing punctuation (after trimming wrapping punctuation,
# as encoded entities contain ';'). Unescape entities to avoid
# breaking them by removing ';'.
middle_unescaped = html.unescape(middle)
stripped = middle_unescaped.rstrip(TRAILING_PUNCTUATION_CHARS)
if middle_unescaped != stripped:
trail = middle[len(stripped):] + trail
middle = middle[:len(stripped) - len(middle_unescaped)]
trimmed_something = True
return lead, middle, trail
def is_email_simple(value):
"""Return True if value looks like an email address."""
# An @ must be in the middle of the value.
if '@' not in value or value.startswith('@') or value.endswith('@'):
return False
try:
p1, p2 = value.split('@')
except ValueError:
# value contains more than one @.
return False
# Dot must be in p2 (e.g. example.com)
if '.' not in p2 or p2.startswith('.'):
return False
return True
words = word_split_re.split(str(text))
for i, word in enumerate(words):
if '.' in word or '@' in word or ':' in word:
# lead: Current punctuation trimmed from the beginning of the word.
# middle: Current state of the word.
# trail: Current punctuation trimmed from the end of the word.
lead, middle, trail = '', word, ''
# Deal with punctuation.
lead, middle, trail = trim_punctuation(lead, middle, trail)
# Make URL we want to point to.
url = None
nofollow_attr = ' rel="noopener noreferrer nofollow"' if nofollow else ''
if simple_url_re.match(middle):
url = smart_urlquote(html.unescape(middle))
elif simple_url_2_re.match(middle):
url = smart_urlquote('http://%s' % html.unescape(middle))
elif ':' not in middle and is_email_simple(middle):
local, domain = middle.rsplit('@', 1)
try:
domain = punycode(domain) # type: ignore
except UnicodeError:
continue
url = 'mailto:%s@%s' % (local, domain)
nofollow_attr = ''
# Make link.
if url:
trimmed = trim_url(middle)
if autoescape and not safe_input:
lead, trail = html.escape(lead), html.escape(trail)
trimmed = html.escape(trimmed)
middle = '<a href="%s"%s>%s</a>' % (html.escape(url),
nofollow_attr, trimmed)
words[i] = mark_safe('%s%s%s' % (lead, middle, trail))
else:
if safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = html.escape(word)
elif safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = html.escape(word)
return ''.join(words)
def link_to(title, url, attrs):
final_attrs = {'href': mark_safe(smart_urlquote(url))}
if attrs:
final_attrs.update(attrs)
return format_html('<a {1}>{0}</a>', force_text(title),
flatatt(final_attrs))
def generate_xml():
root = ElementTree.Element('yml_catalog')
root.set('date', datetime.now().strftime("%Y-%m-%d %H:%M"))
shop = ElementTree.SubElement(root, 'shop')
ElementTree.SubElement(shop, 'name').text = settings.SITE_TITLE
ElementTree.SubElement(shop, 'company').text = u'ИП Морозов Денис Владимирович'
ElementTree.SubElement(shop, 'url').text = 'azbuka-kamnya.ru'
ElementTree.SubElement(shop, 'platform').text = 'Mezzanine'
ElementTree.SubElement(shop, 'version').text = '3.1.5'
ElementTree.SubElement(shop, 'email').text = '*****@*****.**'
currencies = ElementTree.SubElement(shop, 'currencies')
ElementTree.SubElement(currencies, 'currency', id = 'RUR', rate='1')
ElementTree.SubElement(currencies, 'currency', id = 'USD', rate='CBRF', plus='2')
ElementTree.SubElement(currencies, 'currency', id = 'EUR', rate='CBRF', plus='2')
categories = ElementTree.SubElement(shop, 'categories')
for category in Page.objects.published().filter(content_model='category'):
if category.parent_id:
ElementTree.SubElement(categories,
'category',
id=str(category.id),
parentId=str(category.parent_id)
).text = category.title
else:
ElementTree.SubElement(categories,
str('category'),
id=str(category.id)
).text = category.title
ElementTree.SubElement(shop, 'local_delivery_cost').text = '0'
offers = ElementTree.SubElement(shop, 'offers')
for product in Product.objects.published():
if not product.unit_price or product.content_model == 'productstone':
continue
offer = ElementTree.SubElement(
offers,
'offer',
id=str(product.id),
type='vendor.model',
available='false',
bid='10',
cbid='10'
)
ElementTree.SubElement(offer, 'url').text = 'http://azbuka-kamnya.ru' + product.get_absolute_url()
ElementTree.SubElement(offer, 'price').text = str(product.unit_price)
ElementTree.SubElement(offer, 'currencyId').text = CURRENCIES[product.currency]
ElementTree.SubElement(offer, 'categoryId').text = str(product.categories.all()[0].id)
if product.image:
ElementTree.SubElement(offer, 'picture').text = \
'http://azbuka-kamnya.ru' + settings.MEDIA_URL + smart_urlquote(product.image)
ElementTree.SubElement(offer, 'store').text = 'true'
ElementTree.SubElement(offer, 'pickup').text = 'true'
ElementTree.SubElement(offer, 'delivery').text = 'true'
ElementTree.SubElement(offer, 'typePrefix').text = \
getattr(product, product.content_model)._meta.verbose_name.title()
ElementTree.SubElement(offer, 'vendor').text = product.get_manufacturer_display()
ElementTree.SubElement(offer, 'model').text = \
product.title.replace(product.get_manufacturer_display(), u'')
ElementTree.SubElement(offer, 'description').text = product.description
ElementTree.SubElement(offer, 'sales_notes').text = u'Необходима предоплата'
for name, value in getattr(product, product.content_model).get_characteristics().items():
if not value:
continue
unit = None
name = unicode(name)
if len(name.split(',')) > 1:
name, unit = name.split(',')
if unit:
ElementTree.SubElement(offer, 'param', name=name, unit=unit.strip()).text = unicode(value)
else:
ElementTree.SubElement(offer, 'param', name=name).text = unicode(value)
tree = ElementTree.ElementTree(root).getroot()
doctype = """<?xml version='1.0' encoding='UTF-8'?>
<!DOCTYPE yml_catalog SYSTEM "shops.dtd">"""
xml_string = '\n'.join([doctype, tostring(tree, 'utf-8')])
if settings.DEBUG:
open('products.xml', 'w').write(xml_string)
else:
open('/home/users/9/9252095267/domains/azbuka-kamnya.ru/products.xml', 'w').write(xml_string)