|
from selenium import webdriver |
|
from selenium.webdriver.common.by import By |
|
import streamlit as st |
|
from selenium.webdriver import FirefoxOptions |
|
import re |
|
import logging |
|
|
|
|
|
|
|
def scrape_text(url, n_words=15): |
|
try: |
|
driver = None |
|
logging.warning("Initiated Scraping") |
|
user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36" |
|
opts = FirefoxOptions() |
|
opts.add_argument("--headless") |
|
opts.add_argument(f"user-agent={user_agent}") |
|
driver = webdriver.Firefox(options=opts) |
|
driver.set_page_load_timeout(60) |
|
driver.get(url) |
|
elem = driver.find_element(By.TAG_NAME, "body").text |
|
|
|
|
|
sents = elem.split("\n") |
|
sentence_list = [] |
|
for sent in sents: |
|
sent = sent.strip() |
|
if (len(sent.split()) >= n_words) and (len(re.findall(r"^\w.+[^\w\)\s]$", sent))>0): |
|
sentence_list.append(sent) |
|
driver.quit() |
|
logging.warning("Closed Webdriver") |
|
logging.warning("Successfully scraped text") |
|
if len(sentence_list) < 3: |
|
raise Exception("Found nothing to scrape.") |
|
return " \n\n\n".join(sentence_list) |
|
except: |
|
if driver: |
|
driver.close() |
|
logging.warning("Closed Webdriver") |
|
raise |
|
|
