mirror of
https://github.com/KUlishevgeniy/c22712.git
synced 2026-09-24 08:00:22 +00:00
Merge remote-tracking branch 'origin/master'
This commit is contained in:
Generated
+1
-1
@@ -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 (22712)" project-jdk-type="Python SDK" />
|
||||
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9" project-jdk-type="Python SDK" />
|
||||
</project>
|
||||
Generated
+60
-9
@@ -1,16 +1,28 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="AutoImportSettings">
|
||||
<option name="autoReloadType" value="SELECTIVE" />
|
||||
</component>
|
||||
<component name="ChangeListManager">
|
||||
<list default="true" id="e5615680-c090-497d-a104-1337ed85f850" name="Changes" comment="Первый коммит">
|
||||
<change afterPath="$PROJECT_DIR$/info/discord" 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" />
|
||||
<option name="LAST_RESOLUTION" value="IGNORE" />
|
||||
</component>
|
||||
<component name="FileTemplateManagerImpl">
|
||||
<option name="RECENT_TEMPLATES">
|
||||
<list>
|
||||
<option value="Python Script" />
|
||||
</list>
|
||||
</option>
|
||||
</component>
|
||||
<component name="Git.Rebase.Settings">
|
||||
<option name="NEW_BASE" value="master" />
|
||||
</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" />
|
||||
@@ -21,10 +33,15 @@
|
||||
<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" />
|
||||
</component>
|
||||
<component name="PropertiesComponent">{
|
||||
"keyToString": {
|
||||
"RunOnceActivity.OpenProjectViewOnStart": "true",
|
||||
"RunOnceActivity.ShowReadmeOnStart": "true",
|
||||
"WebServerToolWindowFactoryState": "false",
|
||||
"last_opened_file_path": "C:/Users/Alex/c22712",
|
||||
"settings.editor.selected.configurable": "vcs.Git"
|
||||
}
|
||||
}</component>
|
||||
<component name="RunManager">
|
||||
<configuration name="main" type="PythonConfigurationType" factoryName="Python" nameIsGenerated="true">
|
||||
<module name="22712" />
|
||||
@@ -38,6 +55,7 @@
|
||||
<option name="IS_MODULE_SDK" value="true" />
|
||||
<option name="ADD_CONTENT_ROOTS" value="true" />
|
||||
<option name="ADD_SOURCE_ROOTS" value="true" />
|
||||
<EXTENSION ID="PythonCoverageRunConfigurationExtension" runner="coverage.py" />
|
||||
<option name="SCRIPT_NAME" value="$PROJECT_DIR$/main.py" />
|
||||
<option name="PARAMETERS" value="" />
|
||||
<option name="SHOW_COMMAND_LINE" value="false" />
|
||||
@@ -56,6 +74,7 @@
|
||||
<option name="number" value="Default" />
|
||||
<option name="presentableId" value="Default" />
|
||||
<updated>1675926797018</updated>
|
||||
<workItem from="1675931304992" duration="324000" />
|
||||
</task>
|
||||
<task id="LOCAL-00001" summary="Первый коммит">
|
||||
<created>1675927078342</created>
|
||||
@@ -64,9 +83,40 @@
|
||||
<option name="project" value="LOCAL" />
|
||||
<updated>1675927078342</updated>
|
||||
</task>
|
||||
<option name="localTasksCounter" value="2" />
|
||||
<task id="LOCAL-00002" summary="Первый коммит">
|
||||
<created>1675931967836</created>
|
||||
<option name="number" value="00002" />
|
||||
<option name="presentableId" value="LOCAL-00002" />
|
||||
<option name="project" value="LOCAL" />
|
||||
<updated>1675931967836</updated>
|
||||
</task>
|
||||
<task id="LOCAL-00003" summary="Первый коммит">
|
||||
<created>1676532721150</created>
|
||||
<option name="number" value="00003" />
|
||||
<option name="presentableId" value="LOCAL-00003" />
|
||||
<option name="project" value="LOCAL" />
|
||||
<updated>1676532721150</updated>
|
||||
</task>
|
||||
<task id="LOCAL-00004" summary="Первый коммит">
|
||||
<created>1676532798232</created>
|
||||
<option name="number" value="00004" />
|
||||
<option name="presentableId" value="LOCAL-00004" />
|
||||
<option name="project" value="LOCAL" />
|
||||
<updated>1676532798232</updated>
|
||||
</task>
|
||||
<task id="LOCAL-00005" summary="parser">
|
||||
<created>1676934066947</created>
|
||||
<option name="number" value="00005" />
|
||||
<option name="presentableId" value="LOCAL-00005" />
|
||||
<option name="project" value="LOCAL" />
|
||||
<updated>1676934066947</updated>
|
||||
</task>
|
||||
<option name="localTasksCounter" value="6" />
|
||||
<servers />
|
||||
</component>
|
||||
<component name="TypeScriptGeneratedFilesManager">
|
||||
<option name="version" value="3" />
|
||||
</component>
|
||||
<component name="Vcs.Log.Tabs.Properties">
|
||||
<option name="TAB_STATES">
|
||||
<map>
|
||||
@@ -80,7 +130,8 @@
|
||||
</component>
|
||||
<component name="VcsManagerConfiguration">
|
||||
<MESSAGE value="Первый коммит" />
|
||||
<option name="LAST_COMMIT_MESSAGE" value="Первый коммит" />
|
||||
<MESSAGE value="parser" />
|
||||
<option name="LAST_COMMIT_MESSAGE" value="parser" />
|
||||
</component>
|
||||
<component name="XDebuggerManager">
|
||||
<breakpoint-manager>
|
||||
|
||||
@@ -0,0 +1,2 @@
|
||||
Did you know diarrhea is hereditary?
|
||||
It runs in your jeans
|
||||
@@ -0,0 +1,18 @@
|
||||
from bs4 import BeautifulSoup
|
||||
from selenium import webdriver
|
||||
from selenium.webdriver.chrome.service import Service
|
||||
import time
|
||||
|
||||
S = Service('D:\teach\Prog\chromedriver.exe') #Открыли драйвер для хрома
|
||||
browser = webdriver.Chrome(service=S) #Инициировали в отдельную переменную
|
||||
browser.get('https://www.kinopoisk.ru/lists/movies/top250/')
|
||||
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)
|
||||
@@ -0,0 +1 @@
|
||||
Тестовый файл
|
||||
@@ -0,0 +1,13 @@
|
||||
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://pythonpip.ru/examples/kak-posmotret-ustanovlennye-moduli-python-i-vyvesti-ih-spisok')
|
||||
html_text = browser.page_source
|
||||
print(html_text)
|
||||
soup = BeautifulSoup(html_text, 'lxml')
|
||||
infos = soup.find_all(attrs={"class":"relpost-block-single-text"})
|
||||
for info in infos:
|
||||
print(info.text)
|
||||
@@ -0,0 +1 @@
|
||||
Задание1
|
||||
@@ -0,0 +1,12 @@
|
||||
from bs4 import BeautifulSoup
|
||||
from selenium import webdriver
|
||||
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/")
|
||||
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)
|
||||
@@ -0,0 +1 @@
|
||||
Hello World!
|
||||
@@ -0,0 +1,9 @@
|
||||
#made by dialuna (or just Diana Gasanova) <3
|
||||
import requests
|
||||
from bs4 import BeautifulSoup as bs
|
||||
URL = "https://www.kinopoisk.ru/lists/movies/top-250-2020/"
|
||||
r = requests.get(URL, timeout=10)
|
||||
soup = bs(r.text, "html.parser")
|
||||
films = soup.find_all(attrs={"class": "styles_mainTitle__IFQyZ styles_activeMovieTittle__kJdJj"})
|
||||
for film in films:
|
||||
print(film.text)
|
||||
@@ -0,0 +1 @@
|
||||
print('Hello, World!')
|
||||
@@ -0,0 +1 @@
|
||||
text
|
||||
@@ -0,0 +1,25 @@
|
||||
# pip install selenium bs4
|
||||
|
||||
|
||||
from bs4 import BeautifulSoup
|
||||
from selenium import webdriver
|
||||
from selenium.webdriver.chrome.service import Service
|
||||
from time import sleep
|
||||
|
||||
|
||||
s = Service("C:\\Users\\Alex\\PycharmProjects\\pythonProject\\chromedriver.exe")
|
||||
brow = webdriver.Chrome(service=s)
|
||||
|
||||
# brow.get("https://www.kinopoisk.ru/lists/movies/top250/")
|
||||
brow.get("https://www.revshells.com/")
|
||||
sleep(10)
|
||||
|
||||
html = brow.page_source
|
||||
|
||||
soup = BeautifulSoup(html, "lxml")
|
||||
|
||||
# films = soup.find_all(attrs={"class": "styles_mainTitle__IFQyZ styles_activeMovieTittle__kJdJj"})
|
||||
buttons = soup.find_all(attrs={"class": "list-group-item list-group-item-action"})
|
||||
|
||||
for button in buttons:
|
||||
print(button.text)
|
||||
@@ -0,0 +1 @@
|
||||
test
|
||||
@@ -0,0 +1 @@
|
||||
regterg sdgsd sd
|
||||
@@ -0,0 +1 @@
|
||||
print("Hello, world!")
|
||||
@@ -0,0 +1 @@
|
||||
test
|
||||
@@ -0,0 +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)
|
||||
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("--------")
|
||||
@@ -0,0 +1 @@
|
||||
Ок
|
||||
@@ -0,0 +1 @@
|
||||
hello world
|
||||
@@ -0,0 +1 @@
|
||||
eijdieid
|
||||
@@ -0,0 +1 @@
|
||||
ghg
|
||||
@@ -0,0 +1 @@
|
||||
hello!!
|
||||
@@ -0,0 +1,40 @@
|
||||
# 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
|
||||
|
||||
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.get("https://www.revshells.com/") # получаем html код сайта и другую информацию(она нам не нужна сейчас)
|
||||
|
||||
html = brow.page_source # копируем html код в переменную
|
||||
|
||||
soup = BeautifulSoup(html, "lxml") # создаем специальный парсер
|
||||
|
||||
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
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
gfyfghf
|
||||
@@ -0,0 +1 @@
|
||||
Чатик, чатик
|
||||
@@ -0,0 +1 @@
|
||||
def print_hi(' hello')
|
||||
@@ -0,0 +1 @@
|
||||
Проверка работы.
|
||||
Reference in New Issue
Block a user