Merge remote-tracking branch 'origin/master'

# Conflicts:
#	.idea/workspace.xml
This commit is contained in:
Sklvd
2023-03-25 15:13:19 +03:00
17 changed files with 1046 additions and 89 deletions
+1 -1
View File
@@ -1,4 +1,4 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9" project-jdk-type="Python SDK" />
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11" project-jdk-type="Python SDK" />
</project>
+4 -28
View File
@@ -4,10 +4,7 @@
<option name="autoReloadType" value="SELECTIVE" />
</component>
<component name="ChangeListManager">
<list default="true" id="e5615680-c090-497d-a104-1337ed85f850" name="Changes" comment="for parsing">
<change afterPath="$PROJECT_DIR$/Задания/task1/Kluchinskaya1/parsing_in_bd.py" afterDir="false" />
<change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
</list>
<list default="true" id="e5615680-c090-497d-a104-1337ed85f850" name="Changes" comment="parser" />
<option name="SHOW_DIALOG" value="false" />
<option name="HIGHLIGHT_CONFLICTS" value="true" />
<option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
@@ -25,6 +22,7 @@
</component>
<component name="Git.Settings">
<option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
<option name="UPDATE_TYPE" value="REBASE" />
</component>
<component name="MarkdownSettingsMigration">
<option name="stateVersion" value="1" />
@@ -35,11 +33,6 @@
<option name="hideEmptyMiddlePackages" value="true" />
<option name="showLibraryContents" value="true" />
</component>
<component name="PropertiesComponent">
<property name="RunOnceActivity.OpenProjectViewOnStart" value="true" />
<property name="RunOnceActivity.ShowReadmeOnStart" value="true" />
<property name="last_opened_file_path" value="$PROJECT_DIR$" />
</component>
<component name="RunManager">
<configuration name="main" type="PythonConfigurationType" factoryName="Python" nameIsGenerated="true">
<module name="22712" />
@@ -109,21 +102,7 @@
<option name="project" value="LOCAL" />
<updated>1676934066947</updated>
</task>
<task id="LOCAL-00006" summary="for parsing">
<created>1677183215124</created>
<option name="number" value="00006" />
<option name="presentableId" value="LOCAL-00006" />
<option name="project" value="LOCAL" />
<updated>1677183215124</updated>
</task>
<task id="LOCAL-00007" summary="for parsing">
<created>1677183242833</created>
<option name="number" value="00007" />
<option name="presentableId" value="LOCAL-00007" />
<option name="project" value="LOCAL" />
<updated>1677183242833</updated>
</task>
<option name="localTasksCounter" value="8" />
<option name="localTasksCounter" value="6" />
<servers />
</component>
<component name="TypeScriptGeneratedFilesManager">
@@ -139,14 +118,11 @@
</entry>
</map>
</option>
<option name="oldMeFiltersMigrated" value="true" />
</component>
<component name="VcsManagerConfiguration">
<MESSAGE value="Первый коммит" />
<MESSAGE value="parser" />
<MESSAGE value=" for parsing" />
<MESSAGE value="for parsing" />
<option name="LAST_COMMIT_MESSAGE" value="for parsing" />
<option name="LAST_COMMIT_MESSAGE" value="parser" />
</component>
<component name="XDebuggerManager">
<breakpoint-manager>
+20 -13
View File
@@ -1,16 +1,23 @@
# This is a sample Python script.
from bs4 import BeautifulSoup
from selenium.webdriver import Chrome
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
import time
# Press Shift+F10 to execute it or replace it with your code.
# Press Double Shift to search everywhere for classes, files, tool windows, actions, and settings.
# Selenium - библиотека для автоматизации действий веб браузера, скрапинга
# запускаем браузер
s = Service('C:\data\chrome\chromedriver.exe')
browser = webdriver.Chrome(service=s)
browser.get('https://www.wildberries.ru/catalog/muzhchinam/odezhda/futbolki-i-mayki?bid=3b73ce5a-8eba-45a1-b9b2-0723f7592eac#c145658286')
time.sleep (10)#задержка для ввода капчи
html_text = browser.page_source
soup = BeautifulSoup(html_text, 'lxml')
films=soup.find_all('div', class_='/games/the-elder-scrolls-v-skyrim/')
ratings = soup.find_all('div', class_='KnbCardMark_label__hg6Pg tv-series-mark KnbCardMark_isGreen__G_FLl')
for film, rating in zip(films, ratings):
print(f"Игра:{film.text} | Рейтинг:{rating.text}")
def print_hi(name):
# Use a breakpoint in the code line below to debug your script.
print(f'Hi, {name}') # Press Ctrl+F8 to toggle the breakpoint.
# Press the green button in the gutter to run the script.
if __name__ == '__main__':
print_hi('PyCharm')
# See PyCharm help at https://www.jetbrains.com/help/pycharm/
# Это пример парсинга. Вам необходимо спарсить 1 страницу каталога любого сайта на выбор.
#сайты не должны повторяться
# Спарсить необходимо только Заголовки и описание.
-1
View File
@@ -1 +0,0 @@
Тестовый вап
+42
View File
@@ -0,0 +1,42 @@
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"
print(filename)
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()
+23 -2
View File
@@ -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)
@@ -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
+12
View File
@@ -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)
+4 -4
View File
@@ -4,9 +4,9 @@ from selenium.webdriver.chrome.service import Service
s = Service("E:\data\chromedriver.exe")
browser = webdriver.Chrome(service=s)
browser.get("https://www.litres.ru/fedor-dostoevskiy/prestuplenie-i-nakazanie/")
browser.get("https://ria.ru/")
html_text = browser.page_source
soup = BeautifulSoup(html_text, 'lxml')
books = soup.find_all('div', class_='biblio_book_descr')
for book in books:
print(book.text)
news = soup.find_all('div', class_='cell cell-list')
for new in news:
print(new.text)
+15
View File
@@ -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(" ")
+14 -1
View File
@@ -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)
+7 -7
View File
@@ -1,14 +1,14 @@
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from time import sleep
s = Service("С:\DATA\ChromeDriver\chromedriver.exe")
browser = webdriver.Chrome(service=s)
browser.get("https://www.kinopoisk.ru/lists/movies/top250/")
sleep(15)
browser.get("https://online.metro-cc.ru/category/sladosti-chipsy-sneki/shokolad-batonchiki?from=under_search&is_action=1")
html_text = browser.page_source
soup = BeautifulSoup(html_text, 'lxml')
films = soup.find_all('div', class_="desktop-list-main-info_secondaryTitleSlot__mc0mI")
for film in films:
print(film.text)
print("--------")
products = soup.find_all('a', class_="product-card-name reset-link catalog-2-level-product-card__name style--catalog-2-level-product-card")
prices = soup.find_all('span', class_="product-card-prices__actual color-red")
for product,price in zip(products, prices):
print(f"Продукт: {product.text[3:]}Цена: {price.text}")
print("-"*100)
File diff suppressed because one or more lines are too long
+1
View File
@@ -0,0 +1 @@
test
+14
View File
@@ -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)
+17 -29
View File
@@ -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"
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")
for button in buttons:
# выводим текст каждого тега
print(button.text)
# от сердца и почек
# дарю вам питончик
# made by perfecto
cursor.execute(f"insert into images(link, name) values ('{image}', '{title}')")
conn.commit()
+12
View File
@@ -0,0 +1,12 @@
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
s = Service('D:\Games\data\chromedriver.exe')
browser = webdriver.Chrome(service=s)
browser.get('https://www.volkswagen.ru/polo/')
html_text = browser.page_source
soup = BeautifulSoup(html_text, 'lxml')
car_names = soup.find_all('div', class_='avn001-2_name')
prices = soup.find_all('div', class_='avn001-2_price-container')
for car_name, price in zip(car_names, prices):
print(f"Название машины:{car_name.text} | Цена: {price.text} рублей")