async def process(message: types.Message, state: FSMContext):
await bot.send_chat_action(message.from_user.id, ChatActions.TYPING)
art_list = message.text.split()
for art in art_list:
if art.isdigit() and len(art) % 6 == 0:
continue
else:
await state.finish()
return await message.answer('Неверно введены артикулы!')
async with state.proxy() as data:
try:
for art in art_list:
data['art_list'].append(art)
print(data['art_list'])
except KeyError:
data['art_list'] = art_list
data['current_art'] = art_list[0]
data['message'] = message
current_art = art_list[0]
answer, images = parse(current_art)
async with state.proxy() as data:
data[f'article:{current_art}'] = current_art
data[f'images:{current_art}'] = images
data[f'count:{current_art}'] = 1
data[f'price:{current_art}'] = 0
count = 1
price = 0
answer += bold(f'\nКоличество: {count}\nЦена продажи: {price}р')
async with state.proxy() as data:
data[f'title:{current_art}'] = answer
media = []
for img in images:
media.append(InputMediaPhoto(img))
await bot.send_media_group(
message.from_user.id,
media,
reply_to_message_id=message.message_id,
)
await bot.send_message(
message.from_user.id,
text=emojize(answer),
reply_markup=kb.inline_kb1,
)
async def next_prod(call: CallbackQuery, state: FSMContext):
await call.answer('Ищу следующий товар...')
async with state.proxy() as data:
current_art = data['current_art']
art_list = data['art_list']
message = data['message']
index = art_list.index(current_art)
try:
current_art = data['current_art'] = art_list[index + 1]
except IndexError:
return await bot.send_message(
message.from_user.id,
text='Артикулы обработаны. '
'Вы можете:',
reply_markup=kb.inline_finalize,
)
await bot.send_chat_action(message.from_user.id, ChatActions.TYPING)
await Stage.Q1.set()
answer, images = parse(current_art)
async with state.proxy() as data:
data[f'article:{current_art}'] = current_art
data[f'images:{current_art}'] = images
data[f'count:{current_art}'] = 1
data[f'price:{current_art}'] = 0
count = 1
price = 0
answer += bold(f'\nКоличество: {count}\nЦена продажи: {price}р')
async with state.proxy() as data:
data[f'title:{current_art}'] = answer
media = []
for img in images:
media.append(InputMediaPhoto(img))
await bot.send_media_group(
message.from_user.id,
media,
reply_to_message_id=message.message_id,
)
await bot.send_message(
message.from_user.id,
text=emojize(answer),
reply_markup=kb.inline_kb1,
)
def get_clinical_research(medicament):
if check_input(medicament) == False:
return error()
# Get an alphabet characters list.
alphabet_list = parse(get_html(BASE_URL))
# Find a link for transition to the page with a particular letter.
link_togo = get_first_letter_url(alphabet_list, medicament)
if check_input(link_togo) == False:
return error()
# Get a list of medicaments.
medicament_list = get_medicament_list(link_togo)
# Get a list of medicaments that were find.
medicament_link = find_medicament_matches(medicament_list, medicament)
if check_input(medicament_link) == False:
return error()
# Create a bootstrap table to display data that was found.
html = " <table class='table table-hover'><thead class='thead-dark'><tr><th scope='col'>Страница препарата в регистре лекарственных средств России</th><th scope='col'>Информация о клинических исследованиях</th></tr></thead>"
search_result = ""
warning = ""
for i in medicament_link:
link = "http:" + i['value']
medicament_page = get_html(link)
clinical_trials = parse_clinical_trials(medicament_page)
if clinical_trials == None:
search_result = 'Не найдена'
warning = ""
else:
search_result = 'Найдена'
warning = "class='table-primary'"
html = html + "<tr" + " " + warning + "><td align='left'><a href=" + "'" + link + "'" + " " + "target='_blank' class='text-dark'>" + i[
'key'] + "<a></td>" + "<td align='center'>" + search_result + "</td></tr>"
html = html + '</table>'
mapping = {'page': html}
body = render("index", mapping)
return body
def parse(p):
needless = None
p.contents = tabulations.parse(p.contents)
p.windows_style = None
# if p.contents.find('\r'):
if e_bothering.search(p.contents):
p.contents = p.contents.replace('\r', '')
p.windows_style = True
p.old_contents = p.contents
p.characters, p.contents = characters.parse(p.contents)
debug(p, DEBUG_CHARACTERS)
p.comments, p.contents = comments.parse(p.contents)
debug(p, DEBUG_COMMENTS)
p.strings, p.contents = strings.parse(p.contents)
debug(p, DEBUG_STRINGS)
p.macros, p.contents = macros.parse(p.contents)
debug(p, DEBUG_MACROS)
p.blanks, p.contents = blanks.parse(p.contents)
debug(p, DEBUG_BLANKS)
p.functions, p.contents = functions.parse(p.contents)
debug(p, DEBUG_FUNCTIONS)
p.prototypes, p.contents = prototypes.parse(p.contents)
debug(p, DEBUG_PROTOTYPES)
p.types, p.contents = types.parse(p.contents)
debug(p, DEBUG_TYPES)
p.globals, p.contents = globals.parse(p.contents)
debug(p, DEBUG_GLOBALS)
def __init__(self, size, initial_function=None, resolution=256, line_offset=32,\
x_range=(-5, 5), y_range=(-1, 6.5),\
draw_points=False, verbose=True):
if not isinstance(size, abc.Iterable) or len(size) != 2:
raise TypeError
self.size = size
self.image = pygame.Surface(size, pygame.SRCALPHA)
self.function = functions.parse(initial_function)
self.current_time = 0
self.VERBOSE = verbose
self.RESOLUTION = resolution
self.LINE_OFFSET = line_offset
self.X_RANGE = x_range
self.Y_RANGE = y_range
self.DRAW_POINTS = draw_points
def scraper(url):
"""Scraper function"""
things = []
names = []
html = f.get_html(url)
tags = f.parse(html)
for tag in tags:
things.append(f.chop(tag))
f.remove_first_chunk(things)
f.remove_second_chunk(things, names)
things.clear()
f.remove_last_chunk(names, things)
for name in things:
print(name, end="\n\n\n")
import functions
keywords = []
separators = []
operators = []
identifiers = []
parsed_values = []
symbol_table = []
instructions = []
assembly_instructions = []
functions.load_lists("keyword.txt", keywords)
functions.load_lists("operator.txt", operators)
functions.load_lists("separator.txt", separators)
functions.parse("input.txt", keywords, separators, operators, identifiers,
"output.txt", parsed_values, symbol_table, instructions)
functions.gen_assy(instructions, symbol_table, assembly_instructions,
identifiers)
open('output.txt', 'w').close()
output_file = open("output.txt", "a")
print("=== Start of Symbol Table ===")
output_file.write("=== Start of Symbol Table ===\n")
for x in range(0, len(symbol_table)):
print(symbol_table[x])
output_file.write(str(symbol_table[x]) + '\n')
print("=== Start of Assembly Code ===")
output_file.write("=== Start of Assembly Table ===\n")
for x in range(0, len(assembly_instructions)):
def check():
if os.path.exists(tf.name):
"There is currently a user logged on."
else:
print "You are currently not logged in.\n"
functions.parse(raw_input(">> "))
#!/usr/bin/python
import functions
import lexicon
import synonyms
import config
import game
if config.DEBUG == True:
while 1:
playertypes = raw_input('> ')
words = playertypes.split()
print(words)
sen = functions.parse(words)
print(sen)
s = functions.sanitize_sentence(sen)
print(s)
s = functions.synonymize(s)
print("synonyms: ",s)
functions.check_commands(s)
else:
while 1:
playertypes = raw_input('> ')
words = playertypes.split()
sen = functions.parse(words)
s = functions.sanitize_sentence(sen)
s = functions.synonymize(s)
functions.check_commands(s)
import requests
from bs4 import BeautifulSoup
import pandas as pd
from functions import parse
result = pd.DataFrame()
url = 'https://dominos.by'
r = requests.get(url)
soup = BeautifulSoup(r.text, features='html.parser')
div = soup.find_all('div', {'class': 'product-card'})
for item in div:
res = parse(item)
result = result.append(res, ignore_index=True)
result.to_excel('result.xlsx')
def set_function(self, f):
f = functions.parse(f, verbose=self.VERBOSE)
if f:
self.function = f
def indeed_crawl_query():
print("Getting request...")
values = request.get_json()
# Expecting JSON like:
# {
# locations: ['Washington, DC', 'Charlotte, NC', 'Roanoke, VA']
# titles: ['Data Scientist', 'Data Analyst']
# query: """I use python to collect and scrape data from the web. I can set up integrated data pipelines
# pipeline to collect data from different sources. I train machine learning models using sklearn,
# and tensorflow with keras. BeautifulSoup and Selenium. BeautifulSoup and Selenium.
# BeautifulSoup and Selenium. BeautifulSoup and Selenium. I can give results to developers using Flask apps
# and Flask APIs API. I can access APIs API and RSS feeds. I can also use SQL, particularly ElephantSQL
# and Postgres. I like venture capital, finance and business consulting. I love to work with
# natural language processing. Looking for a junior or entry level entry-level or mid level mid-level
# venture capital, finance and business consulting venture capital, finance and business consulting
# venture capital, finance and business consulting venture capital, finance and business consulting"""
# }
# Extract request data
locations = values['locations']
titles = values['titles']
query = values['query']
# Disable auto-complete
print("Launching browser...")
profile = webdriver.FirefoxProfile()
profile.set_preference("browser.formfill.enable", "false")
# Create new Instance of Chrome in incognito mode
browser = webdriver.Firefox(
executable_path='../../../Selenium/geckodriver')
# Instantiate dirty_jobs
dirty_jobs = []
# Crawl over indeed.com
jobs = indeed_crawl(titles, locations, dirty_jobs, browser)
# Clean up the text from the lxml
print('Parsing descriptions...')
texts = parse(jobs)
texts = [str(text)[1:-1] for text in texts]
# Send to df
df = pd.DataFrame(texts, columns=['description'])
df['jobs'] = jobs
# NLP Model
print('Loading model...')
nlp = spacy.load("en_core_web_md")
print('Done loading model!')
# Clean and tokenize the descriptions
# df['tokens'] = [tokenize(entry, nlp) for entry in df['description'].apply(clean_description).tolist()]
# send clean text to list
text = df['description'].apply(clean_description).tolist()
# Instantiate Vectorizer
print('Fitting vectorizer...')
tfidf_dtm = fit_for_nn(text)
# Create a vocab and get word counts per doc
sparse = tfidf.fit_transform(text)
# send to df
tfidf_dtm = pd.DataFrame(sparse.todense(),
columns=tfidf.get_feature_names())
# Instantiate model
print('Teaching the computer...')
nn = NearestNeighbors(n_neighbors=20, algorithm='ball_tree')
nn.fit(tfidf_dtm)
print('Damn, that computer is smart.')
# Process query for the model
print('Asking the computer for recommendations...')
query_dtm = process_query_for_nn(query)
# Query for closest neighbors
results = nn.kneighbors(query_dtm)[1][0].tolist()
# Send to list
job_urls = df['jobs'][results].tolist()
print('Done!')
return jsonify({'jobs': job_urls})
# Extract the directory path to where to find the vocabs
originDir = os.path.dirname(os.path.abspath(__file__))
dir = os.path.join(os.path.dirname(os.path.dirname(originDir)), "Resources")
# Iterate for every directory
for dirName in os.listdir(dir):
# For each directory create a new ExcelFile
if (os.path.isdir(os.path.join(dir, dirName))):
# Create a Pandas Excel writer using XlsxWriter as the engine.
writer = pd.ExcelWriter(os.path.join(originDir, dirName) + ".xlsx",
engine='xlsxwriter',
options={
'strings_to_urls': False,
'constant_memory': True
})
excel = ExcelFile(writer)
# Get the xlsxwriter workbook and worksheet objects.
workbook = writer.book
# Add WorkSheet with relative title and relative bold header
data = workbook.add_worksheet("Data")
data.write_row(0, 0, ("Subject", "Predicate", "Object", "Domain"),
workbook.add_format({"bold": True}))
data.set_column(0, 4, 66)
# Add information for each file of the directory
for fileName in os.listdir(os.path.join(dir, dirName)):
excel = parse(dir, dirName, fileName, excel, originDir)
# Close the Excel file
excel.writer.book.close()
excel.writer.save()