Spaces:
Sleeping
Sleeping
File size: 3,699 Bytes
ce2c98f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 | import pandas as pd
import requests
import time
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
# ======================================
# CREATE DRIVER
# ======================================
def create_driver():
chrome_options = Options()
chrome_options.add_argument("--headless")
chrome_options.add_argument("--no-sandbox")
chrome_options.add_argument("--disable-dev-shm-usage")
chrome_options.add_argument("--disable-gpu")
chrome_options.binary_location = "/usr/bin/chromium"
service = Service("/usr/bin/chromedriver")
driver = webdriver.Chrome(
service=service,
options=chrome_options
)
return driver
# ======================================
# STATIC SCRAPER
# ======================================
def extract_static(url):
try:
headers = {
"User-Agent": (
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
"AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/124.0.0.0 Safari/537.36"
)
}
response = requests.get(
url,
headers=headers,
timeout=15
)
soup = BeautifulSoup(
response.text,
"html.parser"
)
headline = ""
if soup.title:
headline = soup.title.text.strip()
paragraphs = []
for p in soup.find_all("p"):
text = p.get_text(" ", strip=True)
if len(text) > 40:
paragraphs.append(text)
article = "\n".join(paragraphs)
if len(article) > 100:
return headline, article
return None, None
except:
return None, None
# ======================================
# SELENIUM SCRAPER
# ======================================
def extract_selenium(driver, url):
try:
driver.get(url)
time.sleep(3)
soup = BeautifulSoup(
driver.page_source,
"html.parser"
)
headline = ""
h1 = soup.find("h1")
if h1:
headline = h1.text.strip()
paragraphs = []
for p in soup.find_all("p"):
text = p.get_text(" ", strip=True)
if len(text) > 40:
paragraphs.append(text)
article = "\n".join(paragraphs)
if len(article) > 100:
return headline, article
return None, None
except:
return None, None
# ======================================
# MAIN SCRAPER
# ======================================
def scrape_news(file_path):
df = pd.read_excel(file_path)
links = df["Link"].dropna().tolist()
driver = create_driver()
output_file = "scraped_news.txt"
with open(output_file, "w", encoding="utf-8") as f:
for idx, link in enumerate(links, start=1):
headline, article = extract_static(link)
if not headline or not article:
headline, article = extract_selenium(
driver,
link
)
if headline and article:
f.write("\n")
f.write("=" * 100)
f.write("\n")
f.write(f"ARTICLE {idx}\n")
f.write("=" * 100)
f.write("\n\n")
f.write(f"TITLE:\n{headline}\n\n")
f.write(f"URL:\n{link}\n\n")
f.write("CONTENT:\n\n")
f.write(article)
f.write("\n\n")
driver.quit()
return output_file |