public-mirrors/NewsBlur-viq
1
0
Fork 0
mirror of https://github.com/viq/NewsBlur.git synced 2025-09-18 21:43:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

De-vendorizing pynliner.

Browse source
This commit is contained in:
Samuel Clay 2021-04-19 14:06:33 -04:00
parent 6e93a92f64
commit f281b7cd5e
4 changed files with 2 additions and 377 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
apps/social/models.py
View file

@ -12,6 +12,7 @@ import random
import requests
import html.parser as html_parser
import tweepy
import pynliner
from collections import defaultdict
from bs4 import BeautifulSoup
from mongoengine.queryset import Q
@ -30,7 +31,6 @@ from apps.rss_feeds.text_importer import TextImporter
from apps.rss_feeds.page_importer import PageImporter
from apps.profile.models import Profile, MSentEmail
from vendor import facebook
from vendor import pynliner
from utils import log as logging
from utils import json_functions as json
from utils.feed_functions import relative_timesince, chunks

1
config/requirements.txt
View file

@ -52,6 +52,7 @@ pytest==6.1.2
python-dateutil==2.8.1
python-digitalocean==1.16.0
python-gflags==3.1.2
pynliner==0.8
pytz==2020.4
pyyaml==5.3.1
raven==6.10.0

247
vendor/pynliner/__init__.py vendored
View file

@ -1,247 +0,0 @@
#!/usr/bin/env python
"""Pynliner : Convert CSS to inline styles
Python CSS-to-inline-styles conversion tool for HTML using BeautifulSoup and cssutils
Copyright (c) 2011 Tanner Netterville
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
The generated output of this software shall not be used in a mass marketing service.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
"""
__version__ = "0.4.0"
import urllib.request
import cssutils
from bs4 import BeautifulSoup
from .soupselect import select
class Pynliner(object):
"""Pynliner class"""
soup = False
style_string = False
stylesheet = False
output = False
def __init__(self, log=None):
self.log = log
cssutils.log.enabled = False if log is None else True
def from_url(self, url):
"""Gets remote HTML page for conversion
Downloads HTML page from `url` as a string and passes it to the
`from_string` method. Also sets `self.root_url` and `self.relative_url`
for use in importing <link> elements.
Returns self.
>>> p = Pynliner()
>>> p.from_url('http://somewebsite.com/file.html')
<Pynliner object at 0x26ac70>
"""
self.url = url
self.relative_url = '/'.join(url.split('/')[:-1]) + '/'
self.root_url = '/'.join(url.split('/')[:3])
self.source_string = self._get_url(self.url)
return self
def from_string(self, string):
"""Generates a Pynliner object from the given HTML string.
Returns self.
>>> p = Pynliner()
>>> p.from_string('<style>h1 { color:#ffcc00; }</style><h1>Hello World!</h1>')
<Pynliner object at 0x26ac70>
"""
self.source_string = string
return self
def with_cssString(self, cssString):
"""Adds external CSS to the Pynliner object. Can be "chained".
Returns self.
>>> html = "<h1>Hello World!</h1>"
>>> css = "h1 { color:#ffcc00; }"
>>> p = Pynliner()
>>> p.from_string(html).with_cssString(css)
<pynliner.Pynliner object at 0x2ca810>
"""
if not self.style_string:
self.style_string = cssString + '\n'
else:
self.style_string += cssString + '\n'
return self
def run(self):
"""Applies each step of the process if they have not already been
performed.
Returns Unicode output with applied styles.
>>> html = "<style>h1 { color:#ffcc00; }</style><h1>Hello World!</h1>"
>>> Pynliner().from_string(html).run()
u'<h1 style="color: #fc0">Hello World!</h1>'
"""
if not self.soup:
self._get_soup()
if not self.stylesheet:
self._get_styles()
self._apply_styles()
return self._get_output()
def _get_url(self, url):
"""Returns the response content from the given url
"""
return urllib.request.urlopen(url).read()
def _get_soup(self):
"""Convert source string to BeautifulSoup object. Sets it to self.soup.
If using mod_wgsi, use html5 parsing to prevent BeautifulSoup incompatibility.
"""
# Check if mod_wsgi is running - see http://code.google.com/p/modwsgi/wiki/TipsAndTricks
try:
from mod_wsgi import version
self.soup = BeautifulSoup(self.source_string, "html5lib")
except:
self.soup = BeautifulSoup(self.source_string)
def _get_styles(self):
"""Gets all CSS content from and removes all <link rel="stylesheet"> and
<style> tags concatenating into one CSS string which is then parsed with
cssutils and the resulting CSSStyleSheet object set to
`self.stylesheet`.
"""
self._get_external_styles()
self._get_internal_styles()
cssparser = cssutils.CSSParser(log=self.log)
self.stylesheet = cssparser.parseString(self.style_string)
def _get_external_styles(self):
"""Gets <link> element styles
"""
if not self.style_string:
self.style_string = ''
else:
self.style_string += '\n'
link_tags = self.soup.findAll('link', {'rel': 'stylesheet'})
for tag in link_tags:
url = tag['href']
if url.startswith('http://'):
pass
elif url.startswith('/'):
url = self.root_url + url
else:
url = self.relative_url + url
self.style_string += self._get_url(url)
tag.extract()
def _get_internal_styles(self):
"""Gets <style> element styles
"""
if not self.style_string:
self.style_string = ''
else:
self.style_string += '\n'
style_tags = self.soup.findAll('style')
for tag in style_tags:
self.style_string += '\n'.join(tag.contents) + '\n'
tag.extract()
def _get_specificity_from_list(self, lst):
"""
Takes an array of ints and returns an integer formed
by adding all ints multiplied by the power of 10 of the current index
(1, 0, 0, 1) => (1 * 10**3) + (0 * 10**2) + (0 * 10**1) + (1 * 10**0) => 1001
"""
return int(''.join(map(str, lst)))
def _get_rule_specificity(self, rule):
"""
For a given CSSRule get its selector specificity in base 10
"""
return sum(map(self._get_specificity_from_list, (s.specificity for s in rule.selectorList)))
def _apply_styles(self):
"""Steps through CSS rules and applies each to all the proper elements
as @style attributes prepending any current @style attributes.
"""
rules = self.stylesheet.cssRules.rulesOfType(1)
elem_prop_map = {}
elem_style_map = {}
# build up a property list for every styled element
for rule in rules:
# select elements for every selector
selectors = rule.selectorText.split(',')
elements = []
for selector in selectors:
elements += select(self.soup, selector)
# build prop_list for each selected element
for elem in elements:
if elem not in elem_prop_map:
elem_prop_map[elem] = []
elem_prop_map[elem].append({
'specificity': self._get_rule_specificity(rule),
'props': rule.style.getProperties(),
})
# build up another property list using selector specificity
for elem, props in list(elem_prop_map.items()):
if elem not in elem_style_map:
elem_style_map[elem] = cssutils.css.CSSStyleDeclaration()
# ascending sort of prop_lists based on specificity
props = sorted(props, key=lambda p: p['specificity'])
# for each prop_list, apply to CSSStyleDeclaration
for prop_list in [obj['props'] for obj in props]:
for prop in prop_list:
elem_style_map[elem][prop.name] = prop.value
# apply rules to elements
for elem, style_declaration in list(elem_style_map.items()):
if 'style' in elem:
elem['style'] = '%s; %s' % (style_declaration.cssText.replace('\n', ' '), elem['style'])
else:
elem['style'] = style_declaration.cssText.replace('\n', ' ')
def _get_output(self):
"""Generate Unicode string of `self.soup` and set it to `self.output`
Returns self.output
"""
self.output = str(self.soup)
return self.output
def fromURL(url, log=None):
"""Shortcut Pynliner constructor. Equivelent to:
>>> Pynliner().from_url(someURL).run()
Returns processed HTML string.
"""
return Pynliner(log).from_url(url).run()
def fromString(string, log=None):
"""Shortcut Pynliner constructor. Equivelent to:
>>> Pynliner().from_string(someString).run()
Returns processed HTML string.
"""
return Pynliner(log).from_string(string).run()

129
vendor/pynliner/soupselect.py vendored
View file

@ -1,129 +0,0 @@
"""
# Included with pynliner since it isn't on PyPI #
soupselect.py
CSS selector support for BeautifulSoup.
soup = BeautifulSoup('<html>...')
select(soup, 'div')
- returns a list of div elements
select(soup, 'div#main ul a')
- returns a list of links inside a ul inside div#main
patched to support multiple class selectors here http://code.google.com/p/soupselect/issues/detail?id=4#c0
"""
import re
tag_re = re.compile('^[a-z0-9]+$')
attribselect_re = re.compile(
r'^(?P<tag>\w+)?\[(?P<attribute>\w+)(?P<operator>[=~\|\^\$\*]?)' +
r'=?"?(?P<value>[^\]"]*)"?\]$'
)
# /^(\w+)\[(\w+)([=~\|\^\$\*]?)=?"?([^\]"]*)"?\]$/
# \---/ \---/\-------------/ \-------/
# | | | |
# | | | The value
# | | ~,|,^,$,* or =
# | Attribute
# Tag
def attribute_checker(operator, attribute, value=''):
"""
Takes an operator, attribute and optional value; returns a function that
will return True for elements that match that combination.
"""
return {
'=': lambda el: el.get(attribute) == value,
# attribute includes value as one of a set of space separated tokens
'~': lambda el: value in el.get(attribute, '').split(),
# attribute starts with value
'^': lambda el: el.get(attribute, '').startswith(value),
# attribute ends with value
'$': lambda el: el.get(attribute, '').endswith(value),
# attribute contains value
'*': lambda el: value in el.get(attribute, ''),
# attribute is either exactly value or starts with value-
'|': lambda el: el.get(attribute, '') == value \
or el.get(attribute, '').startswith('%s-' % value),
}.get(operator, lambda el: attribute in el)
def select(soup, selector):
"""
soup should be a BeautifulSoup instance; selector is a CSS selector
specifying the elements you want to retrieve.
"""
tokens = selector.split()
current_context = [soup]
for token in tokens:
m = attribselect_re.match(token)
if m:
# Attribute selector
tag, attribute, operator, value = m.groups()
if not tag:
tag = True
checker = attribute_checker(operator, attribute, value)
found = []
for context in current_context:
found.extend([el for el in context.findAll(tag) if checker(el)])
current_context = found
continue
if '#' in token:
# ID selector
tag, id = token.split('#', 1)
if not tag:
tag = True
el = current_context[0].find(tag, {'id': id})
if not el:
return [] # No match
current_context = [el]
continue
if '.' in token:
# Class selector
tag, klass = token.split('.', 1)
if not tag:
tag = True
found = []
for context in current_context:
found.extend(
context.findAll(tag,
{'class': lambda attr: attr and set(klass.split('.')).issubset(attr.split())}
)
)
current_context = found
continue
if token == '*':
# Star selector
found = []
for context in current_context:
found.extend(context.findAll(True))
current_context = found
continue
# Here we should just have a regular tag
if not tag_re.match(token):
return []
found = []
for context in current_context:
found.extend(context.findAll(token))
current_context = found
return current_context
def monkeypatch(BeautifulSoupClass=None):
"""
If you don't explicitly state the class to patch, defaults to the most
common import location for BeautifulSoup.
"""
if not BeautifulSoupClass:
from BeautifulSoup import BeautifulSoup as BeautifulSoupClass
BeautifulSoupClass.findSelect = select
def unmonkeypatch(BeautifulSoupClass=None):
if not BeautifulSoupClass:
from BeautifulSoup import BeautifulSoup as BeautifulSoupClass
delattr(BeautifulSoupClass, 'findSelect')