EduSearch/parser.py

# -*- encoding: utf-8 -*-
# 
"""
virtual_env = os.path.expanduser('~/projects/world-it-planet/env')
activate_this = os.path.join(virtual_env, 'bin/activate_this.py')
exec(open(activate_this).read(), dict(__file__=activate_this))
"""

import os, traceback
from bs4 import BeautifulSoup
import random, time, datetime
import requests
from requests.exceptions import ProxyError

from urllib.parse import urlparse, urljoin
import tldextract

# download stopwords corpus, you need to run it once
import nltk
nltk.download("stopwords")
#--------#

from nltk.corpus import stopwords
from pymystem3 import Mystem
from string import punctuation


#декларативное определение
from sqlalchemy import Column, Integer, String, Text, create_engine
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import sessionmaker
from sqlalchemy.sql.expression import func

#---------------------------------- Variables ----------

donors = [
    "http://npedkol.ru/",
    "https://it-events.com/",
    "https://habr.com/ru/all/",
    "https://innopolis.university/",
]

keywords = [
    "олимпиада",
    "хакатон",
    "конкурс"
]

user_agents = [
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:45.0) Gecko/20100101 Firefox/45.0",
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:86.0) Gecko/20100101 Firefox/86.0",
    "Mozilla/5.0 (Windows NT 5.1; rv:23.0) Gecko/20100101 Firefox/23.0",
    "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.62 Safari/537.36",
    "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)",
    "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0)",
    "Mozilla/5.0 (Windows NT 6.1; rv:23.0) Gecko/20100101 Firefox/23.0",
    "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.62 Safari/537.36",
    "Opera/9.80 (Windows NT 5.1) Presto/2.12.388 Version/12.16",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.62 Safari/537.36",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.22 (KHTML, like Gecko) Chrome/25.0.1364.172 YaBrowser/1.7.1364.21027 Safari/537.22",
    "Opera/9.80 (Windows NT 6.1; WOW64) Presto/2.12.388 Version/12.16",
    "Mozilla/5.0 (iPad; CPU OS 6_1_3 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/6.0 Mobile/10B329 Safari/8536.25",
    "Opera/9.80 (Windows NT 6.1; WOW64) Presto/2.12.388 Version/12.15",
    "Mozilla / 5.0 (Macintosh; Intel Mac OS X 10.14; rv: 75.0) Gecko / 20100101 Firefox / 75.0",
    "Mozilla / 5.0 (Windows NT 6.1; Win64; x64; rv: 74.0) Gecko / 20100101 Firefox / 74.0",
    "Mozilla / 5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit / 537.36 (KHTML, как Gecko) Chrome / 80.0.3987.163 Safari / 537.36",
    "Dalvik/2.1.0 (Linux; U; Android 10; Mi 9T MIUI/V12.0.5.0.QFJMIXM)"
]

bad_file_extensions = ["pdf", "doc", "docx"]

#---------------------------------- Variables End ----------




out_s = ""
#Инициализация SQLLite
basedir = os.path.abspath(os.path.dirname(__file__))
SQLALCHEMY_DATABASE_URI = 'sqlite:///' + os.path.join(basedir, 'all.db')
engine = create_engine(SQLALCHEMY_DATABASE_URI, pool_pre_ping=True)
Base = declarative_base()

# класс БД собранной информации
class Links(Base):
    __tablename__ = 'links'
    id = Column(Integer, primary_key=True, autoincrement=True)
    donor = Column(String(255))
    title = Column(String(512))
    href = Column(String(512))
    parse_date = Column(Integer)
    html = Column(Text)
    text = Column(Text)
    lemmas = Column(Text) # набор лемм из текста (мешок слов)
    level = Column(Integer) # уровень вложенности ссылки от корня сайта
    status = Column(Integer) # 0 - не загружена,  1 - загружена, ключевика нет; 2 - ключевик есть, уведомление не отправлено; 3 - уведомление не отправлено

    def __init__(self, donor, title, href, parse_date, html, text, lemmas, level, status):
        self.donor = donor
        self.title = title
        self.href = href
        self.parse_date = parse_date
        self.html = html
        self.text = text
        self.lemmas = lemmas
        self.level = level
        self.status = status

    def __repr__(self):
        return "<Link('%s', '%s')>" % (self.title, self.href)


class Log(Base):
    __tablename__ = 'log'
    id = Column(Integer, primary_key=True, autoincrement=True)
    action = Column(String(64))
    status = Column(String(64))
    time = Column(Integer)
    donor = Column(String(64))

    def __init__(self, action, status, time, donor):
        self.action = action
        self.status = status
        self.time = time
        self.donor = donor

    def __repr__(self):
        return "<Log('%s','%s', '%s')>" % (self.action, self.status)

# Создание таблицы
Base.metadata.create_all(engine)

Session = sessionmaker(bind=engine)
sqllite_session = Session()


# https://www.kaggle.com/code/alxmamaev/how-to-easy-preprocess-russian-text/script

#Create lemmatizer and stopwords list
mystem = Mystem() 
russian_stopwords = stopwords.words("russian")

#Preprocess function
def preprocess_text(text):
    tokens = mystem.lemmatize(text.lower())
    tokens = [token for token in tokens if token not in russian_stopwords\
            and token != " " \
            and token.strip() not in punctuation]
    
    text = " ".join(tokens)
    
    return text


# парсим по случайных 10 ссылок за раз
for i in range(0, 10):
    link = sqllite_session.query(Links).filter(Links.status == 0).order_by(func.random()).first()
    print("Парсим ", link.href)
    
    #формируем запрос
    user_agent = random.choice(user_agents)
    donor_parsed = urlparse(link.href)
    
    headers = {
            "Host": str(donor_parsed.hostname),
            'User-Agent': str(user_agent),
            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
            'Accept-Language': 'ru-RU,ru;q=0.8,en-US;q=0.5,en;q=0.3',
            'Accept-Encoding': 'gzip, deflate, br',
            'Referer': str(link.href),
            'Upgrade-Insecure-Requests': '1',
            'Connection': 'keep-alive'}

    response = requests.get(link.href, headers=headers)
    print("status_code: ", response.status_code)
    if (response.status_code == 200):
        link.html = response.text
        soup = BeautifulSoup(response.text, "lxml")
        title = str(soup.find('title').string.strip())
        print("title: ", title)
        link.title = title

        text = soup.get_text()
        link.text = text

        lemmas = preprocess_text(text)
        print(lemmas)
        print()



    print()