Last active
September 10, 2021 09:50
-
-
Save gstru/02ec642a3b057d9421fe67e1245198f2 to your computer and use it in GitHub Desktop.
Script to read news without scrolling
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from selenium import webdriver | |
from selenium.webdriver.chrome.options import Options | |
import requests | |
import time | |
from urllib.parse import unquote, urlparse | |
import datetime | |
import openpyxl | |
filename = 'path/data.xlsm' | |
wb = openpyxl.load_workbook(filename) | |
ws = wb['Sites'] | |
news = [] | |
column = ws['A'] | |
for x in range(1, len(column)): | |
news.append(column[x].value) | |
print('Ho caricato le riviste') | |
options = webdriver.ChromeOptions() | |
options.add_extension("path/ublock.crx") | |
options.add_extension("path/I-don't-care-about-cookies.crx") | |
options.add_argument('--disable-gpu') | |
options.add_argument("--log-level=0") | |
options.add_argument("--log-level=1") | |
options.add_argument("--log-level=2") | |
options.add_argument("--log-level=3") | |
options.add_argument("--ignore-certificate-errors") | |
options.add_argument("--start-maximized") | |
driver = webdriver.Chrome(executable_path=r'path/chromedriver.exe', options=options) | |
SCROLL_PAUSE_TIME = 0.015 | |
def scroll(): | |
driver.execute_script("window.scrollBy(0, 2.5)") | |
i = 0 | |
news_num = len(news)-1 | |
while True: | |
driver.get(news[i]) | |
driver.execute_script("document.body.style.zoom='100%'") | |
t_end = time.time() + 15 | |
while time.time() < t_end: | |
scroll() | |
time.sleep(SCROLL_PAUSE_TIME) | |
if i == news_num: | |
driver.close() | |
driver.quit() | |
break | |
i = i + 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment