def show_highlight(news, article_url):
news = news.upper()
article_url = articles.find_one({'title': article_url})['url']
print(article_url)
if news in known_news:
# article_url = 'https://www.foxnews.com/us/man-arrested-for-stabbing-baby-trump-protest-balloon-at-alabama-lsu-game'
highlight(article_url, d)
return render_template('highlighted_article.html')
else:
return '404'
def color_palette(*args):
"""
Prints out names, (hex and/or RGB and/or numerical values)
for each of the web-safe HTML-supported colors, in color.
"""
from highlight import highlight
for color_name, hex_value in color_names.items():
c = convert_color(hex_value, 'num')
highlight(' ' + color_name + ' ',
c,
False,
fill='#',
width=42,
alignment='center')
if 'hex' in args:
highlight(hex_value, c, False, width=42, alignment='center')
if 'rgb' in args:
highlight(convert_color(hex_value, 'rgb'),
c,
False,
width=42,
alignment='center')
if 'num' in args:
highlight(convert_color(hex_value, 'num'),
c,
False,
width=42,
alignment='center')
def call(name, args, wd=None):
logger = logging.getLogger(highlight(name))
logger.info("starting %s...", args)
master, slave = pty.openpty()
process = subprocess.Popen(args,
bufsize=1,
stdin=slave,
stdout=slave,
stderr=subprocess.STDOUT,
close_fds=True,
cwd=wd)
os.close(slave)
process.stdout = os.fdopen(master)
try:
while True:
line = process.stdout.readline()
if not line: break
line = line.replace("\n", "")
if "\r" in line:
line = de_ret(line)
logger.info(line)
except IOError as e:
if e.errno == 5:
pass
else:
raise
return process.wait()
def _debug(model: models.Model, event: str):
model = replace(model, mode=0)
model_dict = asdict(model)
model_dict.pop("debug_model_length")
model_dict.pop("debug_model_text")
# strip Escape sequences from highlighted content for readability
for tab in model_dict['tabs']:
if tab and not tab['selected_file']['is_dir']:
tab['selected_file']['content'] = [
blesses.strip_esc(line)
for line in tab['selected_file']['content']
]
model_json = json.dumps(model_dict, indent=2)
if model.code_hilighting:
model = replace(model,
debug_model_text=highlight(model_json,
"json").split("\n"))
else:
model = replace(model, debug_model_text=model_json.split("\n"))
model = replace(
model,
debug_model_text=model.debug_model_text[0:len(model.debug_model_text) -
1])
model = replace(model, debug_model_length=len(model.debug_model_text))
return model
def view(self):
data = {
"page": self._get_page_data(),
"ctxnav": list(self.environ._ctxnav("view", self.name)),
}
data["html"] = highlight(data["page"]["text"], mime=self.mime)
return self.render("view.html", **data)
def show_results(self):
""" show table of results"""
doc['container'].clear()
doc['container'] <= html.DIV(
'Browser Version: %s' % window.navigator.userAgent)
_v = sys.implementation.version
doc['container'] <= html.DIV('Brython Version: %s.%s.%s' %
(_v.major, _v.minor, _v.micro))
doc['container'] <= html.DIV(
'Brython debug mode: %s' % sys.brython_debug_mode)
doc['container'] <= html.DIV(
'CPython Version: %s' % self.cpython_version)
doc['container'] <= html.P(html.I('Results are in milliseconds (ms)'))
_table = html.TABLE()
_tr = html.TR()
_tr <= html.TH('Benchmark')
_tr <= html.TH('Code')
_tr <= html.TH('Brython')
_tr <= html.TH('CPython')
_tr <= html.TH('Difference')
_tr <= html.TH('X Faster')
_table <= _tr
for _filename in self._timings.keys():
_tr = html.TR()
_tr <= html.TD(_filename)
_tr <= html.TD(
highlight.highlight(self._timings[_filename]['code']))
for _platform in ('brython', 'cpython'):
_tr <= html.TD('%5.0f' % self._timings[_filename][_platform],
style={'text-align': 'right'})
_diff = self._timings[_filename]['cpython'] - self._timings[
_filename]['brython']
_x = self._timings[_filename]['cpython'] / self._timings[
_filename]['brython']
if _x > 1:
_color = "green"
elif _x < 0.5:
_color = "red"
else:
_color = "black"
_tr <= html.TD('%5.0f' % _diff, style={'text-align': 'right'})
_tr <= html.TD('%4.2f' % _x,
style={
'color': _color,
'text-align': 'right'
})
_table <= _tr
doc['container'] <= _table
def show_page(slideshow, zone, page_num):
# if table of contents is not empty, add it
if slideshow.contents:
toc = html.SELECT(name="toc")
toc.bind(
'change', lambda ev: show_page(
slideshow, zone,
int(ev.target.options[ev.target.selectedIndex].value)))
for content in slideshow.contents:
toc <= html.OPTION(
content[0], value=content[1], selected=page_num >= content[1])
slideshow.page_num = int(page_num)
# store page num in a cookie
document.cookie = "page={}".format(page_num)
zone.clear()
body = html.DIV()
body.html = markdown.mark(slideshow.pages[page_num])[0]
if slideshow.contents:
body = html.DIV(toc + body)
footer = html.DIV(Id="footer")
if slideshow.title:
footer <= html.DIV(slideshow.title, style=dict(display='inline'))
if slideshow.show_page_num:
footer <= html.SPAN(' (%s/%s)' % (page_num + 1, len(slideshow.pages)),
style=dict(display='inline'))
timeline = html.DIV(Id='timeline')
tl_pos = html.DIV(Id='tl_pos')
timeline <= tl_pos
timeline.bind('click', lambda ev: move_to(ev, slideshow, zone))
tl_pos.bind('click', click_on_tl_pos)
zone <= body + footer + timeline
wh = window.innerHeight
footer.style.top = "{}px".format(int(wh * 0.9))
timeline.style.top = "{}px".format(int(wh * 0.85))
tl_pos.style.left = '%spx' % (timeline.width * page_num /
len(slideshow.pages))
document["cours"].style.minHeight = "{}px".format(int(wh * 0.8))
for elt in zone.get(selector='.python'):
src = elt.text.strip()
width = max(len(line) for line in src.split('\n'))
width = max(width, 30)
# replace element content by highlighted code
elt.html = highlight.highlight(src).html
elt.style.width = '%sem' % int(0.7 * width)
elt.bind('click', run_code)
def xml(self):
language = self['language'] or 'PYTHON'
link = self['link']
counter = self.attributes.get('counter', 1)
styles = self['styles'] or {}
return highlight(
''.join(self.components),
language=language,
link=link,
counter=counter,
styles=styles,
attributes=self.attributes,
)
def xml(self):
language = self['language'] or 'PYTHON'
link = self['link']
counter = self.attributes.get('counter', 1)
styles = self['styles'] or {}
return highlight(
''.join(self.components),
language=language,
link=link,
counter=counter,
styles=styles,
attributes=self.attributes,
)
def load(url, target):
# fake query string to bypass browser cache
qs = "?foo=%s" % time.time()
try:
mk, scripts = markdown.mark(open(url + qs).read())
except IOError:
doc[target].html = "Page %s not found" % url
return False
doc[target].html = mk
for script in scripts:
exec(script)
for elt in doc[target].get(selector=".exec"):
# Python code executed when user clicks on a button
elt.contentEditable = True
src = elt.text.strip()
h = highlight.highlight(src)
h.className = "pycode"
elt.clear()
elt <= h
elt.focus()
btn = html.BUTTON("▶")
btn.bind("click", run)
elt.parent.insertBefore(btn, elt)
for elt in doc[target].get(selector=".exec_on_load"):
# Python code executed on page load
src = elt.text.strip()
h = highlight.highlight(src)
h.className = "pycode"
elt.clear()
elt <= h
exec(src)
for elt in doc[target].get(selector=".python"):
src = elt.text.strip()
h = highlight.highlight(src)
h.className = "pycode"
elt.clear()
elt <= h
return False
def load(url, target):
# fake query string to bypass browser cache
qs = '?foo=%s' % time.time()
try:
mk, scripts = markdown.mark(open(url + qs).read())
except IOError:
doc[target].html = "Page %s not found" % url
return False
doc[target].html = mk
for script in scripts:
exec(script)
for elt in doc[target].get(selector='.exec'):
# Python code executed when user clicks on a button
elt.contentEditable = True
src = elt.text.strip()
h = highlight.highlight(src)
h.className = "pycode"
elt.clear()
elt <= h
elt.focus()
btn = html.BUTTON('▶')
btn.bind('click', run)
elt.parent.insertBefore(btn, elt)
for elt in doc[target].get(selector='.exec_on_load'):
# Python code executed on page load
src = elt.text.strip()
h = highlight.highlight(src)
h.className = "pycode"
elt.clear()
elt <= h
exec(src)
for elt in doc[target].get(selector='.python'):
src = elt.text.strip()
h = highlight.highlight(src)
h.className = "pycode"
elt.clear()
elt <= h
return False
def main():
for file_name in ("main.py", "highlight.py",
"lexer.py"): # opens the files and prints them
with open(file_name, 'r') as f:
code = f.read()
print("File: " + file_name)
skip_pos, highlights = highlight.highlight(highlight.parse(code))
i = 0
while i < len(highlights):
c = highlights[i]
print(c, end='', flush=True)
time.sleep(0.05)
i += 1
def show_results(self):
""" show table of results"""
doc['container'].clear()
doc['container'] <= html.DIV('Browser Version: %s' % window.navigator.userAgent)
_v=sys.implementation.version
doc['container'] <= html.DIV('Brython Version: %s.%s.%s' % (_v.major, _v.minor, _v.micro))
doc['container'] <= html.DIV('Brython debug mode: %s' % sys.brython_debug_mode)
doc['container'] <= html.DIV('CPython Version: %s' % self.cpython_version)
doc['container'] <= html.P(html.I('Results are in milliseconds (ms)'))
_table=html.TABLE()
_tr=html.TR()
_tr <= html.TH('Benchmark')
_tr <= html.TH('Code')
_tr <= html.TH('Brython')
_tr <= html.TH('CPython')
_tr <= html.TH('Difference')
_tr <= html.TH('X Faster')
_table <= _tr
for _filename in self._timings.keys():
_tr=html.TR()
_tr <= html.TD(_filename)
_tr <= html.TD(highlight.highlight(self._timings[_filename]['code']))
for _platform in ('brython', 'cpython'):
_tr <= html.TD('%5.0f' % self._timings[_filename][_platform],
style={'text-align':'right'})
_diff=self._timings[_filename]['cpython'] - self._timings[_filename]['brython']
_x=self._timings[_filename]['cpython']/self._timings[_filename]['brython']
if _x > 1:
_color="green"
elif _x < 0.5:
_color="red"
else:
_color="black"
_tr <= html.TD('%5.0f' % _diff,
style={'text-align':'right'})
_tr <= html.TD('%4.2f' % _x,
style={'color': _color,
'text-align':'right'})
_table <= _tr
doc['container'] <= _table
def search(course_name, keyword):
files = glob('./data/*')
filename = sorted(files)[-1]
crawling_time = re.search(r'[0-9]{10}', filename).group()
with open(filename, 'rb') as f:
tree = pickle.load(f)
data = {}
data['results'] = []
data['crawling_time'] = crawling_time
for pre, fill, node in tree:
if hasattr(node, 'content') and node.parent.name == course_name:
res = highlight(node.content, keyword)
if len(res):
data['results'].append({
'highlights': res,
'url': node.url,
'title': node.name
})
return data
def hi_sentence(sent, features):
locs = []
ans = sent['annotation']
lemmas = ans['lemma']
posses = ans['pos']
for ft in features:
for lm in lemmas:
ft_str = ft[:-2]
ft_pos = ft[-1:]
if lm['label'] == ft_str:
def is_match(pos):
return ((pos['begin'] == lm['begin'])
and (pos['label'][0] == ft_pos))
# at most one, of course...
for p in filter(is_match, posses):
loc = int(p['begin']), int(p['length'])
locs.append(loc)
return highlight(sent['display'], locs, 'green')
def hi_sentence(sent, features):
locs = []
ans = sent['annotation']
lemmas = ans['lemma']
posses = ans['pos']
for ft in features:
for lm in lemmas:
ft_str = ft[:-2]
ft_pos = ft[-1:]
if lm['label'] == ft_str:
def is_match(pos):
return (
(pos['begin'] == lm['begin']) and
(pos['label'][0] == ft_pos)
)
# at most one, of course...
for p in filter(is_match, posses):
loc = int(p['begin']), int(p['length'])
locs.append(loc)
return highlight(sent['display'], locs, 'green')
def show_page(slideshow, zone, page_num):
# if table of contents is not empty, add it
if slideshow.contents:
toc = html.SELECT(name="toc")
toc.bind('change', lambda ev: show_page(slideshow, zone,
int(ev.target.options[ev.target.selectedIndex].value)))
for content in slideshow.contents:
toc <= html.OPTION(content[0], value=content[1],
selected=page_num>=content[1])
slideshow.page_num = int(page_num)
zone.clear()
body = html.DIV()
body.html = markdown.mark(slideshow.pages[page_num])[0]
if slideshow.contents:
body = html.DIV(toc+body)
footer = html.DIV(Id="footer")
if slideshow.title:
footer <= html.DIV(slideshow.title,style=dict(display='inline'))
if slideshow.show_page_num:
footer <= html.SPAN(' (%s/%s)' %(page_num+1, len(slideshow.pages)),
style=dict(display='inline'))
timeline = html.DIV(Id='timeline')
tl_pos = html.DIV(Id='tl_pos')
timeline <= tl_pos
timeline.bind('click', lambda ev:move_to(ev, slideshow, zone))
tl_pos.bind('click', click_on_tl_pos)
zone <= body+footer+timeline
tl_pos.style.left = '%spx' %(timeline.width*page_num/len(slideshow.pages))
for elt in zone.get(selector='.python'):
src = elt.text.strip()
width = max(len(line) for line in src.split('\n'))
# replace element content by highlighted code
elt.html = highlight.highlight(src).html
elt.style.width = '%sem' %int(0.7*width)
def diff(self, *args, **kwargs):
name = os.path.sep.join(args)
rev = kwargs["rev"]
to_rev = int(rev)
from_rev = to_rev - 1
text = self.storage.revision_text(name, from_rev).split("\n")
other = self.storage.revision_text(name, to_rev).split("\n")
to_date = ""
from_date = ""
date_format = "%Y-%m-%dT%H:%M:%SZ"
for history in self.storage.page_history(name):
if history[0] == to_rev:
to_date = history[1]
elif history[0] == from_rev:
from_date = history[1]
if not from_date:
from_date = to_date
diff = "\n".join(
unified_diff(text, other, "%s@%d" % (name, from_rev),
"%s@%d" % (name, to_rev),
strftime(date_format, gmtime(from_date)),
strftime(date_format, gmtime(to_date))))
data = {
"title": "diff of %s from %s to %s" % (name, from_rev, to_rev),
"diff": highlight(diff, lang="diff"),
}
return self.render("diff.html", **data)
def diff(self, *args, **kwargs):
name = os.path.sep.join(args)
rev = kwargs["rev"]
to_rev = int(rev)
from_rev = to_rev - 1
text = self.storage.revision_text(name, from_rev).split("\n")
other = self.storage.revision_text(name, to_rev).split("\n")
to_date = ""
from_date = ""
date_format = "%Y-%m-%dT%H:%M:%SZ"
for history in self.storage.page_history(name):
if history[0] == to_rev:
to_date = history[1]
elif history[0] == from_rev:
from_date = history[1]
if not from_date:
from_date = to_date
diff = "\n".join(unified_diff(text, other,
"%s@%d" % (name, from_rev),
"%s@%d" % (name, to_rev),
strftime(date_format, gmtime(from_date)),
strftime(date_format, gmtime(to_date))))
data = {
"title": "diff of %s from %s to %s" % (name, from_rev, to_rev),
"diff": highlight(diff, lang="diff"),
}
return self.render("diff.html", **data)
lines = []
tokens = []
def match(query, line):
return all(w in line for w in query)
def search(q):
return [line for line in tokens if match(q, line)]
for line in open('tokenized_quotes.txt'):
L = line.split()
tokens.append(L)
print('No, dalej!')
t0 = time.time()
for x in sys.stdin:
L = x.split()
print(green('QUERY: ') + ' '.join(L))
search(L)
for res in search(L):
print(' ', highlight(L, res))
yellow_line()
print()
print(time.time() - t0)
def simulate_console_statement(varname,
function=None,
args=[],
assign='',
module=None,
comment=None):
highlight('>>> ' + varname + ' = ', 'white')
if module:
print module + '.',
if function:
highlight(function, 'orange')
highlight('(', 'white')
if args:
if str.isdigit(str(args[0])) or isinstance(args[0], (int, float)):
highlight(args[0], 'yellow')
else:
try:
args[0].index('=')
l, r = args[0].split('=')
highlight(l + '=', 'white')
if str.isdigit(r):
highlight(r, 'yellow')
else:
highlight(r, 'green')
except:
highlight(args[0], 'green')
for each in args[1:]:
highlight(', ', 'white')
if str.isdigit(str(each)):
highlight(each, 'yellow')
else:
try:
each.index('=')
l, r = each.split('=')
highlight(l + '=', 'white')
if str.isdigit(r):
highlight(r, 'yellow')
else:
highlight(r, 'green')
except:
highlight(args[0], 'green')
highlight(')', 'white')
elif assign:
if isinstance(assign, (int, float)):
highlight(assign, 'yellow')
else:
highlight(assign, 'green')
if comment:
highlight(' # ' + comment, 'gray')
print
def simulate_console_function(function, args, module=MODULE, comment=None):
highlight('>>> ' + module + '.', 'white')
highlight(function, 'orange')
highlight('(', 'white')
if args:
if str.isdigit(str(args[0])) or isinstance(args[0], (int, float)):
highlight(args[0], 'yellow')
else:
try:
args[0].index('=')
l, r = args[0].split('=')
highlight(l + '=', 'white')
if str.isdigit(r):
highlight(r, 'yellow')
else:
highlight(r, 'green')
except:
highlight(args[0], 'green')
for each in args[1:]:
highlight(', ', 'white')
if str.isdigit(str(each)):
highlight(each, 'yellow')
else:
try:
each.index('=')
l, r = each.split('=')
highlight(l + '=', 'white')
if str.isdigit(r):
highlight(r, 'yellow')
else:
highlight(r, 'green')
except:
highlight(args[0], 'green')
highlight(')', 'white')
if comment:
highlight(' # ' + comment, 'gray')
print
def border():
highlight('*' * 42, 'blue', False)
else:
highlight(r, 'green')
except:
highlight(args[0], 'green')
highlight(')', 'white')
elif assign:
if isinstance(assign, (int, float)):
highlight(assign, 'yellow')
else:
highlight(assign, 'green')
if comment:
highlight(' # ' + comment, 'gray')
print
highlight('- formatlib.numbers -'.center(42), 'green', False)
print
border()
print fl.zero_lead.__doc__
simulate_console_function('zero_lead', [2], comment=fl.zero_lead(2))
simulate_console_function('zero_lead', [12], comment=fl.zero_lead(12))
simulate_console_function('zero_lead', [2, 3], comment=fl.zero_lead(2, 3))
print
border()
print fl.zero_trail.__doc__
def show_page(slideshow, zone, page_num):
# if table of contents is not empty, add it
if slideshow.contents:
toc = html.SELECT(name="toc")
toc.bind('change', lambda ev: show_page(slideshow, zone,
int(ev.target.options[ev.target.selectedIndex].value)))
for content in slideshow.contents:
toc <= html.OPTION(content[0], value=content[1],
selected=page_num>=content[1])
slideshow.page_num = int(page_num)
# store page num in a cookie
document.cookie = "page={}".format(page_num)
zone.clear()
body = html.DIV()
body.html = markdown.mark(slideshow.pages[page_num])[0]
if slideshow.contents:
body = html.DIV(toc + body)
footer = html.DIV(Id="footer")
if slideshow.title:
footer <= html.DIV(slideshow.title,style=dict(display='inline'))
if slideshow.show_page_num:
footer <= html.SPAN(' (%s/%s)' %(page_num+1, len(slideshow.pages)),
style=dict(display='inline'))
timeline = html.DIV(Id='timeline')
tl_pos = html.DIV(Id='tl_pos')
timeline <= tl_pos
timeline.bind('click', lambda ev:move_to(ev, slideshow, zone))
tl_pos.bind('click', click_on_tl_pos)
zone <= body + footer +timeline
wh = window.innerHeight
footer.style.top = "{}px".format(int(wh * 0.9))
timeline.style.top = "{}px".format(int(wh * 0.85))
tl_pos.style.left = '%spx' %(timeline.width*page_num/len(slideshow.pages))
document["cours"].style.minHeight = "{}px".format(int(wh * 0.8))
for elt in zone.get(selector='.python'):
src = elt.text.strip()
width = max(len(line) for line in src.split('\n'))
width = max(width, 30)
# replace element content by highlighted code
elt.html = highlight.highlight(src).html
elt.style.width = '%sem' %int(0.7*width)
elt.bind('click', run_code)
for elt in zone.get(selector='.python-console'):
src = elt.text.strip()
lines = src.split('\n')
result = ''
py = ''
py_starts = []
for line in lines:
if line.startswith('>>>') or line.startswith('...'):
py += line[4:]+'\n'
py_starts.append('<span class="python-prompt">{}</span>'.format(line[:3]))
else:
if py:
colored = highlight.highlight(py).html
colored_lines = colored.split('\n')
if result:
result += '\n'
result += '\n'.join(start+' '+line
for (start, line) in zip(py_starts, colored_lines))
py = ''
py_starts = []
result += '\n' + line
if py:
colored = highlight.highlight(py).html
colored_lines = colored.split('\n')
if result:
result += '\n'
result += '\n'.join(start+' '+line
for (start, line) in zip(py_starts, colored_lines))
py = ''
py_starts = []
elt.html = result
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import Select
browser = webdriver.Chrome()
FirstName = "Phoenix"
LastName = "Wright"
Email = "*****@*****.**"
PassWord = "******"
browser.get('https://courses.ultimateqa.com/users/sign_in')
elem = browser.find_element_by_link_text('Create a new account')
highlight.highlight(elem) #highlights link about to be clicked
browser.implicitly_wait(5)
elem.click()
elem = browser.find_element_by_id('user_first_name')
elem.send_keys(FirstName)
elem = browser.find_element_by_id('user_last_name')
elem.send_keys(LastName)
elem = browser.find_element_by_id('user_email')
elem.send_keys(Email)
elem = browser.find_element_by_id('user_password')
elem.send_keys(PassWord + Keys.ENTER)
#copied
print()
def analyze():
start = time.time()
# Receives the input query from form
if request.method == 'POST':
'''global rawtext
global phrases
global important
global bold'''
rawtext = request.form['rawtext']
# Analysis
docx = nlp(rawtext)
phrases = extract.phrases(rawtext)
important = extract.important(rawtext)
important = list(set(important))
bold = extract.bold(rawtext)
bold = list(set(bold))
# Tokens
custom_tokens = [token.text for token in docx]
#print(custom_tokens)
#print(bold)
#print(important)
#print('\n\n')
#print(phrases)
text = highlight.highlight(rawtext, phrases, bold, important)
print(text)
initial = """
<html>
<head>
<title>Text Highlighted</title>
<style>
a { color: #ff6600; transition: .5s; -moz-transition: .5s; -webkit-transition: .5s; -o-transition: .5s; font-family: 'Muli', sans-serif; }
a:hover { text-decoration: underline }
h1 { padding-bottom: 15px }
h1 a { font-family: 'Open Sans Condensed', sans-serif; font-size: 48px; color: #333; }
h1 a:hover { color: #ff6600; text-decoration: none; }
p { color: #333; font-family: 'Muli', sans-serif; margin-bottom: 15px; }
a.more-link { color: white; font-weight: bold; font-size: 14px; font-family: Arial, Helvetica, sans-serif; padding: 3px 10px; background-color: #ff6600; border-radius: 5px; float: right; }
a.more-link:hover { text-decoration: none; background-color: #666; border-radius: 0px; }
</style>
</head>
<body>
<p>"""
towrite = initial + text + """</p></body></html"""
f = open('templates/doc.html', 'w', encoding="utf8")
f.write(towrite)
f.close()
print(text)
f = open('text.txt', 'w')
f.write(rawtext)
f.close()
# Word Info
custom_wordinfo = [(token.text, token.lemma_, token.shape_,
token.is_alpha, token.is_stop) for token in docx]
custom_postagging = [(word.text, word.tag_, word.pos_, word.dep_)
for word in docx]
# NER
custom_namedentities = [(entity.text, entity.label_)
for entity in docx.ents]
blob = TextBlob(rawtext)
blob_sentiment, blob_subjectivity = blob.sentiment.polarity, blob.sentiment.subjectivity
# allData = ['Token:{},Tag:{},POS:{},Dependency:{},Lemma:{},Shape:{},Alpha:{},IsStopword:{}'.format(token.text,token.tag_,token.pos_,token.dep_,token.lemma_,token.shape_,token.is_alpha,token.is_stop) for token in docx ]
allData = [(
'"Token":"{}","Tag":"{}","POS":"{}","Dependency":"{}","Lemma":"{}","Shape":"{}","Alpha":"{}","IsStopword":"{}"'
.format(token.text, token.tag_, token.pos_, token.dep_,
token.lemma_, token.shape_, token.is_alpha, token.is_stop))
for token in docx]
result_json = json.dumps(allData, sort_keys=False, indent=2)
end = time.time()
final_time = end - start
return render_template('index.html',
ctext=rawtext,
custom_tokens=phrases,
custom_postagging=bold,
custom_namedentities=important,
custom_wordinfo=text,
blob_sentiment=bold,
blob_subjectivity=blob_subjectivity,
final_time=final_time,
result_json=result_json)
def show_page(slideshow, zone, page_num):
# if table of contents is not empty, add it
if slideshow.contents:
toc = html.SELECT(name="toc")
toc.bind('change', lambda ev: show_page(slideshow, zone,
int(ev.target.options[ev.target.selectedIndex].value)))
for content in slideshow.contents:
toc <= html.OPTION(content[0], value=content[1],
selected=page_num>=content[1])
slideshow.page_num = int(page_num)
# store page num in a cookie
document.cookie = "page={}".format(page_num)
zone.clear()
body = html.DIV()
body.html = markdown.mark(slideshow.pages[page_num])[0]
wh = window.innerHeight
fontSize = int(18 * window.innerHeight / 800)
body.style.fontSize = "{}px".format(fontSize)
if slideshow.contents:
body = html.DIV(toc + body)
footer = html.DIV(Id="footer")
footer.style.fontSize = "{}px".format(fontSize)
if slideshow.title:
footer <= html.DIV(slideshow.title,style=dict(display='inline'))
if slideshow.show_page_num:
footer <= html.SPAN(' (%s/%s)' %(page_num+1, len(slideshow.pages)),
style=dict(display='inline'))
timeline = html.DIV(Id='timeline')
timeline.style.height = "{}px".format(int(fontSize/2))
tl_pos = html.DIV(Id='tl_pos')
timeline <= tl_pos
timeline.bind('click', lambda ev:move_to(ev, slideshow, zone))
tl_pos.bind('click', click_on_tl_pos)
zone <= body + footer + timeline
wh = window.innerHeight
tl_pos.style.left = '%spx' %(timeline.width*page_num/len(slideshow.pages))
document["cours"].style.minHeight = "{}px".format(int(wh * 0.9))
for elt in zone.get(selector='.python'):
src = elt.text.strip()
width = max(len(line) for line in src.split('\n'))
width = max(width, 30)
# replace element content by highlighted code
elt.html = highlight.highlight(src).html
elt.style.width = '%sem' %int(0.7*width)
elt.bind('click', run_code)
for elt in zone.get(selector='.python-console'):
src = elt.text.strip()
lines = src.split('\n')
result = ''
py = ''
py_starts = []
for line in lines:
if line.startswith('>>>') or line.startswith('...'):
py += line[4:]+'\n'
py_starts.append('<span class="python-prompt">{}</span>'.format(line[:3]))
else:
if py:
colored = highlight.highlight(py).html
colored_lines = colored.split('\n')
if result:
result += '\n'
result += '\n'.join(start+' '+line
for (start, line) in zip(py_starts, colored_lines))
py = ''
py_starts = []
else:
line = escape(line)
result += '\n' + line
if py:
colored = highlight.highlight(py).html
colored_lines = colored.split('\n')
if result:
result += '\n'
result += '\n'.join(start+' '+line
for (start, line) in zip(py_starts, colored_lines))
py = ''
py_starts = []
elt.html = result
if re.match(r':?/?([.a-zA-Z0-9_-]+/)+', fileName):
directory = fileName[:fileName.rfind('/')+1]
numSentences = int(input('Number of sentences in summary: '))
numKey = int(input('Number of key phrases: '))
text = PDF2Text(fileName)
print('---text loaded---')
clean(text)
print('---cleaned---')
summarize('cleantext.txt', numSentences, directory)
print('---summarized---')
keyphrases = get_key_phrases(numKey, directory)
print('---key phrases found---')
make_pdf(keyphrases, directory)
print('---pdf made---')
highlight(keyphrases, directory)
print('---pdf highlighted---')
if platform.system() == 'Windows':
subprocess.run(['del', 'cur_img.png'], shell = True)
subprocess.run(['del', 'cur_txt.txt'], shell = True)
subprocess.run(['del', 'cur_pdf.pdf'], shell = True)
subprocess.run(['del', 'cleantext.txt'], shell = True)
subprocess.run(['del', 'searchable.pdf'], shell = True)
else:
subprocess.run(['rm', 'cur_img.png'])
subprocess.run(['rm', 'cur_txt.txt'])
subprocess.run(['rm', 'cur_pdf.pdf'])
subprocess.run(['rm', 'cleantext.txt'])
subprocess.run(['rm', 'searchable.pdf'])
print('done')
def enter_url():
if request.method == 'GET':
return render_template('enter_url.html')
else:
highlight(request.form['url'], d)
return render_template('highlighted_article.html')
