141 lines
5.4 KiB
Python
141 lines
5.4 KiB
Python
import os
|
|
import requests
|
|
import requests_html
|
|
from requests_html import HTMLSession
|
|
from bs4 import BeautifulSoup
|
|
|
|
class NewsScraper:
|
|
def __init__(self, url, title_selector, time_selector, item_selector, show_content=False, enable_js=False, content_selector=None):
|
|
self.url = url
|
|
self.title_selector = title_selector
|
|
self.time_selector = time_selector
|
|
self.item_selector = item_selector
|
|
self.show_content = show_content
|
|
self.enable_js = enable_js
|
|
self.content_selector = content_selector
|
|
|
|
def scrape(self):
|
|
try:
|
|
if self.enable_js:
|
|
session = HTMLSession()
|
|
response = session.get(self.url)
|
|
response.html.render(timeout=20) # Render the JavaScript content (adjust the timeout as needed)
|
|
html = response.html.html
|
|
else:
|
|
response = requests.get(self.url)
|
|
html = response.content
|
|
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
|
|
news_items = []
|
|
|
|
for item in soup.select(self.item_selector):
|
|
title_element = item.select_one(self.title_selector)
|
|
time_element = item.select_one(self.time_selector)
|
|
|
|
if title_element and time_element:
|
|
title = title_element.text.strip()
|
|
time = time_element.text.strip()
|
|
|
|
if self.show_content:
|
|
if self.content_selector:
|
|
content_element = item.select_one(self.content_selector)
|
|
else:
|
|
content_element = item.find('div', class_='field-content')
|
|
|
|
if content_element:
|
|
content = content_element.decode_contents(formatter="html")
|
|
news_item_html = """
|
|
<div class="news-item">
|
|
<h2 class="news-title">{title}</h2>
|
|
<p class="news-time">{time}</p>
|
|
<div class="news-content">{content}</div>
|
|
</div>
|
|
""".format(title=title, time=time, content=content)
|
|
else:
|
|
news_item_html = """
|
|
<div class="news-item">
|
|
<h2 class="news-title">{title}</h2>
|
|
<p class="news-time">{time}</p>
|
|
</div>
|
|
""".format(title=title, time=time)
|
|
else:
|
|
news_item_html = """
|
|
<div class="news-item">
|
|
<h2 class="news-title">{title}</h2>
|
|
<p class="news-time">{time}</p>
|
|
</div>
|
|
""".format(title=title, time=time)
|
|
|
|
news_items.append(news_item_html)
|
|
|
|
return news_items
|
|
except requests.exceptions.RequestException as e:
|
|
print(f"Error fetching URL: {e}")
|
|
return []
|
|
except AttributeError as e:
|
|
print(f"Error parsing HTML: {e}")
|
|
return []
|
|
except Exception as e:
|
|
print(f"Unexpected error: {e}")
|
|
return []
|
|
|
|
def write_to_html(self, template_path, output_path, news_items, heading):
|
|
try:
|
|
with open(template_path, 'r') as f:
|
|
html_template = f.read()
|
|
|
|
news_html = '\n'.join(news_items)
|
|
html_output = html_template.replace('</body>', f'<h1>{heading}</h1>\n{news_html}\n</body>')
|
|
|
|
with open(output_path, 'a') as f:
|
|
f.write(html_output)
|
|
except IOError as e:
|
|
print(f"Error writing to file: {e}")
|
|
except Exception as e:
|
|
print(f"Unexpected error: {e}")
|
|
|
|
# Define the scrapers for each news source
|
|
|
|
almayadeen_scraper = NewsScraper(
|
|
url="https://english.almayadeen.net/shortnews",
|
|
title_selector="h4",
|
|
time_selector="div.post-tag.day-time",
|
|
item_selector="div.item",
|
|
show_content=False,
|
|
enable_js=False
|
|
)
|
|
|
|
middleeasteye_scraper = NewsScraper(
|
|
url="https://www.middleeasteye.net/live/israels-war-gaza-live-israel-pounds-rafah-overnight-strikes",
|
|
title_selector=".views-field.views-field-title-1 span.field-content a",
|
|
time_selector=".views-field.views-field-changed span.field-content",
|
|
item_selector=".views-row",
|
|
show_content=True,
|
|
enable_js=False
|
|
)
|
|
|
|
aljazeera_scraper = NewsScraper(
|
|
url="https://www.aljazeera.com/news/liveblog/2024/4/20/israels-war-on-gaza-live-israelis-continue-intense-raid-on-nur-shams-camp",
|
|
title_selector="h2",
|
|
time_selector=".date-relative__time",
|
|
item_selector=".card-live",
|
|
content_selector=".wysiwyg-content",
|
|
show_content=True,
|
|
enable_js=True
|
|
)
|
|
|
|
# Scrape and write to HTML for each news source
|
|
|
|
if os.path.exists('./index.html'):
|
|
os.remove('./index.html')
|
|
|
|
news_items = almayadeen_scraper.scrape()
|
|
almayadeen_scraper.write_to_html('./template.html', './index.html', news_items, 'Al Mayadeen News')
|
|
|
|
news_items = middleeasteye_scraper.scrape()
|
|
middleeasteye_scraper.write_to_html('./template.html', './index.html', news_items, 'Middle East Eye News')
|
|
|
|
news_items = aljazeera_scraper.scrape()
|
|
aljazeera_scraper.write_to_html('./template.html', './index.html', news_items, 'Al Jazeera News')
|