Merge remote-tracking branch 'origin/master'

Задания/task1/Antipenko/DB1.py

@@ -0,0 +1,41 @@
+import psycopg2
+import wget
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+# Парсер и загрузчик в БД//Антипенко Дмитрий
+connection = psycopg2.connect(host='localhost', dbname='PythonDB', user='postgres', password='Q1w2e3r4')
+
+cursor = connection.cursor()
+
+creat_qwery = """ create table Parser 
+    (id serial primary key, page_name varchar(100), price varchar(10), priceDis varchar(30), mark varchar(10), scr varchar(100))"""
+
+cursor.execute(creat_qwery)
+connection.commit()
+
+driver = Service('D:\teach\Prog\chromedriver.exe') 
+browser = webdriver.Chrome(service=driver)
+browser.get('https://amwine.ru/catalog/igristoe_vino_i_shampanskoe/igristoe_vino/')
+html_code = browser.page_source
+b_soup = BeautifulSoup(html_code, 'lxml')
+name = b_soup.find_all('a', class_="catalog-list-item__title js-product-detail-link")
+price = b_soup.find_all('span', class_="middle_price")
+priceDis = b_soup.find_all('span', class_="baseoldprice")
+mark = b_soup.find_all('span', class_="product-rating__rating")
+pictures = b_soup.find_all('div', class_="catalog-list-item__img-wrapper")
+
+for i in range(15):
+    url = 'https://amwine.ru'+pictures[i].find('a').find('img').attrs['data-src']
+    filename = f"Programming\\23.03\img\{i}.jpg"
+    wget.download(url, filename)
+    ins_qwery = f"""insert into public.Parser(page_name, price, priceDis, mark, scr) values ('{name[i].text}', '{price[i].text}', '{priceDis[i].text}',  '{mark[i].text}', '{filename}')"""
+    cursor.execute(ins_qwery)
+    connection.commit()
+
+
+
+
+cursor.close()
+
+connection.close()

Задания/task1/Antipenko/ada.main.py

@@ -1,3 +1,6 @@
+
+#Вариант с пары
+'''
 from bs4 import BeautifulSoup
 from selenium import webdriver
 from selenium.webdriver.chrome.service import Service
@@ -10,9 +13,27 @@ html_text = browser.page_source
 time.sleep(20)
 soup = BeautifulSoup(html_text, 'lxml')
 films = soup.find_all('div', class_='base-movie-main-info_mainInfo__ZL_u3')
-'''
+
 print(soup)
 print(films)
-'''
+
 for film in films:
     print(film.text)
+'''
+#Домашка
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+
+driver = Service('D:\teach\Prog\chromedriver.exe') 
+browser = webdriver.Chrome(service=driver)
+browser.get('https://hmbrussia.ru/regional-office/')
+html_code = browser.page_source
+b_soup = BeautifulSoup(html_code, 'lxml')
+name = b_soup.find_all('div', class_="ps-xl-3 ms-xl-3")
+
+print(b_soup)
+print(name)
+
+for i in name:
+    print(i.text)

Задания/task1/Epifanov/1 - st hw.py

@@ -8,6 +8,7 @@ browser.get('https://www.rftoday.ru/_vse_zagolovki2')
 html_text = browser.page_source
 soup = BeautifulSoup(html_text, 'lxml')
 infos = soup.find_all(attrs={"class": "title"})
+revs = soup.find_all(attrs={"class": "source"})
 #print(infos[0].text) - если нужно вывести только n-ый заголовок
-for info in infos:
-    print(info.text)#Вывод всех заголовков новостей страницы 1
+for info, rev in zip(infos, revs):
+    print(f"{info.text} ; Источник: {rev.text}")#Вывод всех заголовков новостей и их источников со страницы 1

Задания/task1/Epifanov/FHWDB.py

@@ -0,0 +1,32 @@
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+import psycopg2
+import wget
+
+browser = webdriver.Chrome(service=Service('C:\Desktop\exe\chromedriver.exe'))
+browser.get('https://flawery.ru/moscow/bouquets/event-yanvary25/?min=0&max=max&sorting=discount&filter_24h=on')
+soup = BeautifulSoup(browser.page_source, "lxml")
+Name = soup.find_all(attrs={"class": "catalog_title"})
+Price = soup.find_all(attrs={"class": "catalog_price_now"})
+Delivery_Time = soup.find_all(attrs={"class": "catalog_express"})
+Discount = soup.find_all(attrs={"class": "catalog_sale"})
+Image = soup.find_all(attrs={"class": "catalog_item catalog_item_popup"})
+
+connection = psycopg2.connect(host='localhost', dbname='FHWDB', user='postgres', password='Q1w2e3r4')
+cursor = connection.cursor()
+create_q = '''CREATE TABLE Parse  
+     (ID serial primary key, Name varchar(100), Price varchar(9), Delivery_Time varchar(25), Discount varchar(10), src varchar(110))'''
+cursor.execute(create_q)
+connection.commit()
+
+for j in range(60):
+    url = 'https://flawery.ru'+Image[j].find('a').find('picture').find('img').attrs['src']
+    tempf = f"C:\\Users\\user\\Desktop\\FHWDB{j}.jpg"
+    wget.download(url, tempf)
+    insert_query = f'''INSERT into public.Parse(Name, Price, Delivery_Time, Discount, src) values ('{Name[j].text}', '{Price[j].text}', '{Delivery_Time[j].text}', '{Discount[j].text}', '{tempf}') '''
+    cursor.execute(insert_query)
+
+connection.commit()
+cursor.close()
+connection.close()

Задания/task1/Filcheva/Verst1.py

@@ -0,0 +1,12 @@
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+from time import sleep
+s = Service("C:\Driver\chromedriver.exe")
+browser = webdriver.Chrome(service=s)
+browser.get("https://mephi.ru/")
+sleep(10)
+html_text = browser.page_source
+soup = BeautifulSoup(html_text, "lxml")
+serv = soup.find_all("div", class_="views-field views-field-title menu-item menu-item-10702")
+print(serv[0].text)

Задания/task1/Gasanova/parser.py

@@ -1,4 +1,4 @@
-#made by dialuna (or just Diana Gasanova) <3
+# Diana Gasanova
 import requests
 from bs4 import BeautifulSoup as bs
 URL = "https://www.kinopoisk.ru/lists/movies/top-250-2020/"

Задания/task1/Kluchinskaya1/parsing_in_bd.py

@@ -0,0 +1,26 @@
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+from wget import download
+import psycopg2
+connection = psycopg2.connect(host='localhost', dbname='dbdata',
+                              user='postgres', password='Q1w2e3r4')
+cursor=connection.cursor()
+s = Service('C:\\Users\\Dasha\\Desktop\\Progect\\chromedriver.exe')
+browser = webdriver.Chrome(service=s)
+url = 'https://www.tretyakovgallery.ru/'
+browser.get(url)
+html_text=browser.page_source
+soup = BeautifulSoup(html_text, 'lxml')
+products = soup.find_all(attrs={"class": "building-item"})
+for i, product in enumerate(products):
+    link = product.find("img").attrs.get("src")
+    tag = product.find("strong")
+    if tag is not None:
+        download(url + link, f"img\\{i}.jpg")
+        cursor.execute(f"""INSERT INTO public.parsing(name, link)
+                          VALUES           
+                          ( '{tag.text}', '{url + link}')""")
+connection.commit()
+cursor.close()
+connection.close()

Задания/task1/Kuznetsov/parcing.py

@@ -0,0 +1,15 @@
+from bs4 import BeautifulSoup
+from selenium.webdriver import Chrome
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+import time
+s = Service('E:\\Downloads\\chromedriver_win32.zip\\chromedriver.exe')
+browser = webdriver.Chrome(service=s)
+browser.get('https://trial-sport.ru/gds.php?s=51516&c1=1070639&c2=1070640')
+html_text = browser.page_source
+soup = BeautifulSoup(html_text, 'lxml')
+product_name=soup.find_all('a', class_='title')
+description=soup.find_all('span', class_='description')
+for product_name, description in zip(product_name, description):
+    print(f"Продукт: {product_name.text} \nОписание: {description.text}")
+print(" ")

Задания/task1/Kuznetsov/test

@@ -1 +1,14 @@
-test
+from bs4 import BeautifulSoup
+from selenium.webdriver import Chrome
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+import time
+s = Service('E:\\Downloads\\chromedriver_win32.zip\\chromedriver.exe')
+browser = webdriver.Chrome(service=s)
+browser.get('https://trial-sport.ru/gds.php?s=51516&c1=1070639&c2=1070640')
+html_text = browser.page_source
+soup = BeautifulSoup(html_text, 'lxml')
+bike_name=soup.find_all('a', class_='title')
+print (bike_name[0].text)
+description=soup.find_all('span', class_='description')
+print (description[0].text)

Задания/task1/Lahin/postgres.py

@@ -0,0 +1,71 @@
+import psycopg2
+import wget
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+import time
+i = 1
+s = Service("С:\DATA\ChromeDriver\chromedriver.exe")
+browser = webdriver.Chrome(service=s)
+browser.get("https://www.mvideo.ru/noutbuki-planshety-komputery-8/noutbuki-118?from=under_search")
+height = browser.execute_script("return document.body.scrollHeight")
+time.sleep(4)
+while 900*i < height:
+    height = browser.execute_script("return document.body.scrollHeight")
+    browser.execute_script(f"window.scrollTo(0,{900*i})")
+    time.sleep(1)
+    i+=1
+html_text = browser.page_source
+soup = BeautifulSoup(html_text, 'lxml')
+productst = soup.find_all('a', class_="product-title__text")
+pricest = soup.find_all('span', class_="price__main-value")
+features = soup.find_all('ul', class_="product-feature-list product-feature-list--undefined")
+pictures =  soup.find_all('img', class_="product-picture__img product-picture__img--list")
+products, prices, diagonals, resolutions, CPUs, RAMs, Graphics_controllers, Volumes = [],[],[],[],[],[],[],[]
+for i in range(len(productst)):
+    products.append(productst[i].text.strip())
+    prices.append(pricest[i].text.replace("\xa0", "").strip())
+for feature in features:
+    u = feature.text
+    diagonals.append(u[20:u.find("\"",20)+1])
+    resolutions.append(u[u.find("\"",20)+2:u.find(".", 23)+1])
+    CPUs.append(u[u.find("Процессор",20)+9:u.find("ГГц",20)+3].replace("\xa0",""))
+    RAMs.append(" ".join(u[u.find("(RAM)",20)+5:u.find("Графический контроллер")].split()))
+    Graphics_controllers.append(u[u.find("Графический контроллер")+22:u.rfind("Объем")-2])
+    Volumes.append(u[u.rfind("Объем")+6:].replace("\xa0", "").strip())
+for i in range(len(Volumes)):
+    u = Volumes[i]
+    if u.rfind("D")!=-1: Volumes[i] = u[:u.rfind("D")+1]+ " " + u[u.rfind("D")+1:]
+    else: Volumes[i] = u[:u.rfind("С")+1]+ " " + u[u.rfind("С")+1:]
+connection=psycopg2.connect(host='localhost', dbname='dbdata', user='postgres', password='Q1w2e3r4')
+cursor = connection.cursor()
+insert = """CREATE TABLE public.laptops(
+id serial primary key,
+product varchar(100),
+price varchar(15),
+diagonal varchar(5),
+resolution varchar(20),
+CPU varchar(50),
+RAM varchar(10),
+Graphics_Controller varchar(40),
+Volume varchar(25),
+src varchar(100)
+);
+"""
+cursor.execute(insert)
+connection.commit()
+for i in range(len(products)):
+    url = "https://"+pictures[i]['src']
+    filename = f"C:\DATA\Images\{i+1}.jpg"
+    wget.download(url, filename)
+    insert = f"""INSERT INTO public.laptops(
+        product, price, diagonal, resolution, CPU, RAM, Graphics_Controller, Volume, src)
+        VALUES
+        ('{products[i]}', '{prices[i]}', '{diagonals[i]}', '{resolutions[i]}', '{CPUs[i]}', '{RAMs[i]}', '{Graphics_controllers[i]}', '{Volumes[i]}', '{filename}');"""
+    cursor.execute(insert)
+    connection.commit()
+cursor.execute("select * from laptops")
+print("Результат", cursor.fetchall())
+cursor.close()
+connection.close()
+

Задания/task1/Lahin/postgresEasy.py

@@ -0,0 +1,42 @@
+import psycopg2
+import wget
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+s = Service("С:\DATA\ChromeDriver\chromedriver.exe")
+browser = webdriver.Chrome(service=s)
+browser.get("https://online.metro-cc.ru/virtual/assortiment_rioba-4887?from=under_search&page=2")
+html_text = browser.page_source
+soup = BeautifulSoup(html_text, 'lxml')
+productst = soup.find_all('span', class_="product-card-name__text")
+pricest = soup.find_all('span', class_="product-price__sum-rubles")
+pictures = soup.find_all('img', class_="product-card-photo__image")
+connection=psycopg2.connect(host='localhost', dbname='dbdata', user='postgres', password='Q1w2e3r4')
+cursor = connection.cursor()
+products, prices = [], []
+for i in range(len(productst)):
+    products.append(productst[i].text.replace("\n", "").strip())
+    prices.append(pricest[i].text+" Р/шт")
+insert = """CREATE TABLE public.Chocolate(
+id serial primary key,
+product varchar(100),
+price varchar(25),
+src varchar(50)
+);
+"""
+cursor.execute(insert)
+connection.commit()
+for i in range(len(products)):
+    url = pictures[i]['src']
+    filename = f"C:\DATA\Images2\{i+1}.jpg"
+    wget.download(url, filename)
+    insert = f"""INSERT INTO public.Chocolate(
+        product, price, src)
+        VALUES
+        ('{products[i]}', '{prices[i]}', '{filename}');"""
+    cursor.execute(insert)
+    connection.commit()
+cursor.execute("select * from Chocolate")
+print("Результат", cursor.fetchall())
+cursor.close()
+connection.close()

Задания/task1/Samigullin/test

@@ -0,0 +1 @@
+test

Задания/task1/Sukhanov/DZ_PARSBD.py

@@ -0,0 +1,41 @@
+import psycopg2
+import wget
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+connection = psycopg2.connect(host='localhost', dbname='dbdata', user='postgres', password='Q1w2e3r4')
+
+cursor = connection.cursor()
+
+cr_qwery = """ create table Parser 
+    (id serial primary key, name varchar(100), sale varchar(30), price varchar(10), rate varchar(10), picture varchar(100))"""
+
+#cursor.execute(cr_qwery)
+connection.commit()
+
+driver = Service('D:\GOGdriver\chromedriver.exe')
+browser = webdriver.Chrome(service=driver)
+browser.get('https://www.perekrestok.ru/cat/promo/10')
+html_code = browser.page_source
+soup = BeautifulSoup(html_code, 'lxml')
+
+name = soup.find_all('div', class_="product-card__title")
+sale = soup.find_all('div', class_="sc-kYrlTI ciSrDA product-card__badge")
+price = soup.find_all('div', class_="price-new")
+rate = soup.find_all('div', class_="rating-value")
+picture = soup.find_all('div', class_="product-card__image-wrapper")
+
+for i in range(15):
+    url = picture[i].find('img').attrs['src']
+    filename = f"C:\\Users\\71332\PycharmProjects\pythonProject1\\venv\Pictures\{i}.jpg"
+    wget.download(url, filename)
+    ins_qwery = f"""insert into public.Parser(name, sale, price, rate, picture) values ('{name[i].text}', '{sale[i].text}', '{price[i].text}', '{rate[i].text}', '{filename}')"""
+    cursor.execute(ins_qwery)
+    connection.commit()
+
+
+
+
+cursor.close()
+
+connection.close()

Задания/task1/Sukhanov/zaparsil.py

@@ -0,0 +1,16 @@
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+
+driver = Service('D:\GOGdriver\chromedriver.exe')
+browser = webdriver.Chrome(service=driver)
+browser.get('https://www.kinopoisk.ru/lists/movies/popular-films/')
+html_code = browser.page_source
+soup = BeautifulSoup(html_code, 'lxml')
+name = soup.find_all('div', class_="desktop-list-main-info_secondaryTitleSlot__mc0mI")
+
+print(soup)
+print(name)
+
+for i in name:
+    print(i.text)

Задания/task1/Uskova/parcing.py

@@ -0,0 +1,14 @@
+from bs4 import BeautifulSoup
+from selenium.webdriver import Chrome
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+import time
+s = Service('C:\\Users\\Yekaterina\\Downloads\\chromedriver_win32\\chromedriver.exe')
+browser = webdriver.Chrome(service=s)
+browser.get('https://www.citilink.ru/catalog/noutbuki/')
+html_text = browser.page_source
+soup = BeautifulSoup(html_text, 'lxml')
+name=soup.find_all('div', class_='app-catalog-1tp0ino e1an64qs0')
+print (name[0].text)
+description=soup.find_all('div', class_='app-catalog-1o4umte eevw8x70')
+print (description[0].text)

Задания/task1/Yaroshevskiy/main.py

@@ -1,40 +1,28 @@
-# установи python, pip
-
-# выполни эту команду: pip install selenium bs4 lxml
-# если ты используешь pycharm, то надо библиотеки ставить не в консоли(терминале), а в самом pycharm
-# для этого нажми "view" > "tool windows" > "python packages"
-# внизу в окне поиска ищи нужные библиотеки
-# когда найдешь, нажимай на нее, справа будет кнопка "install package", устанавливай, потом перезапусти pycharm
-
-# найди версию своего браузера
-# напиши в гугле "скачать драйвер для <название и версия твоего браузера> selenium" 
-# теперь все готово для запуска этого
-# помните, что сам сайт(который вы хотите парсить) может вас блокировать или заставлять проходить capture, из-за чего этот код ничего не выведет
-
 from bs4 import BeautifulSoup
 from selenium import webdriver
 from selenium.webdriver.chrome.service import Service
-# импортируем всё нужное
+from wget import download
+import psycopg2 as psyc
 
-s = Service("путь_до_драйвера") # в ковычках указываем полный путь до скаченного ранее драйвера
-# если ты на винде, то вместо знака "\" пиши "\\"
 
-brow = webdriver.Chrome(service=s) # как будто создаем виртуальный браузер
+brow = webdriver.Chrome()
+url = "https://ikey.ru/"
+brow.get(url)
 
-brow.get("https://www.revshells.com/") # получаем html код сайта и другую информацию(она нам не нужна сейчас)
+html = brow.page_source
 
-html = brow.page_source # копируем html код в переменную
+soup = BeautifulSoup(html, "lxml")
 
-soup = BeautifulSoup(html, "lxml") # создаем специальный парсер
+products = soup.find_all(attrs={"class": "product"})
 
-buttons = soup.find_all(attrs={"class": "list-group-item list-group-item-action"})
-# получаем список всех html тегов, в которых есть атрибут "class", равный: "list-group-item list-group-item-action"
-
-for button in buttons:
-    # выводим текст каждого тега
-    print(button.text)
-
-# от сердца и почек
-# дарю вам питончик
-# made by perfecto
+with psyc.connect(dbname="db_for_parse", user="perfecto") as conn:
+    with conn.cursor() as cursor:
+        for i, product in enumerate(products):
+            img_tag = product.find(attrs={"class": "imagef"}).find("img")
+            title = img_tag.attrs.get("alt")
+            image = url + img_tag.attrs.get("src")
+            download(url + img_tag.attrs.get("src"), f"images/{i}.jpg")
 
+            cursor.execute(f"insert into images(link, name) values ('{image}', '{title}')")
+        
+        conn.commit()

Задания/task1/romanov/num1

@@ -1 +1 @@
-def print_hi(' hello')
+абоба

Задания/task1/romanov/parcinghellride.py

@@ -0,0 +1,14 @@
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+
+s = Service('C:\Desktop\exe\chromedriver.exe')
+browser = webdriver.Chrome(service=s)
+browser.get('https://www.hellride.ru/catalog/zapchasti-dlya-tryukovyh-samokatov/deki')
+html_text = browser.page_source
+soup = BeautifulSoup(html_text, 'lxml')
+prices = soup.find_all(attrs={"class": "product-card__price"})
+titles = soup.find_all(attrs={"class": "product-card__title"})
+
+for price, title in zip(prices, titles):
+    print(f" название {title.text} ; цена: {price.text}")