Aditya Amol Patil commited on
Create web_scrap.py
Browse files- web_scrap.py +110 -0
web_scrap.py
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import json
|
| 2 |
+
import os
|
| 3 |
+
import random
|
| 4 |
+
from flask import Flask, jsonify
|
| 5 |
+
import requests
|
| 6 |
+
from bs4 import BeautifulSoup
|
| 7 |
+
|
| 8 |
+
app = Flask(__name__)
|
| 9 |
+
|
| 10 |
+
NEWS_SOURCES = {
|
| 11 |
+
"Hacker News": {"url": "https://news.ycombinator.com/", "selectors": {"article": ".athing", "title": ".storylink", "link": ".storylink"}},
|
| 12 |
+
"FreeCodeCamp": {"url": "https://www.freecodecamp.org/news/", "selectors": {"article": ".post-card", "title": "h2 a", "link": "h2 a", "image": "img"}},
|
| 13 |
+
"Ars Technica": {"url": "https://arstechnica.com/information-technology/", "selectors": {"article": "li.article", "title": "h2 a", "link": "h2 a", "image": "img"}},
|
| 14 |
+
"InfoQ": {"url": "https://www.infoq.com/development/news/", "selectors": {"article": ".news-list .news_item", "title": "h2 a", "link": "h2 a", "image": ".news_image img"}},
|
| 15 |
+
"TechCrunch": {"url": "https://techcrunch.com/startups/", "selectors": {"article": "article", "title": "h2 a", "link": "h2 a", "image": "img"}},
|
| 16 |
+
"Dev.to": {"url": "https://dev.to/", "selectors": {"article": ".crayons-story", "title": "h2 a", "link": "h2 a", "image": "img"}},
|
| 17 |
+
"Google AI Blog": {"url": "https://ai.googleblog.com/", "selectors": {"article": ".date-outer", "title": ".post-title.entry-title a", "link": ".post-title.entry-title a"}},
|
| 18 |
+
"NVIDIA Developer Blog": {"url": "https://developer.nvidia.com/blog/", "selectors": {"article": "article", "title": "h2 a", "link": "h2 a", "image": "img"}},
|
| 19 |
+
"JetBrains Blog": {"url": "https://blog.jetbrains.com/", "selectors": {"article": ".post-item", "title": ".post-title a", "link": ".post-title a", "image": "img"}},
|
| 20 |
+
"Stack Overflow Blog": {"url": "https://stackoverflow.blog/", "selectors": {"article": ".post", "title": "h2 a", "link": "h2 a", "image": "img"}},
|
| 21 |
+
"OpenAI Blog": {"url": "https://openai.com/research/", "selectors": {"article": ".post", "title": "h3 a", "link": "h3 a", "image": "img"}},
|
| 22 |
+
"Smashing Magazine": {"url": "https://www.smashingmagazine.com/articles/", "selectors": {"article": "article", "title": "h2 a", "link": "h2 a", "image": "img"}},
|
| 23 |
+
"TechCrunch": {"url": "https://techcrunch.com/startups/", "selectors": {"article": "article", "title": "h2 a", "link": "h2 a", "image": "img"}},
|
| 24 |
+
"Dev.to": {"url": "https://dev.to/", "selectors": {"article": ".crayons-story", "title": "h2 a", "link": "h2 a", "image": "img"}},
|
| 25 |
+
"Google AI Blog": {"url": "https://ai.googleblog.com/", "selectors": {"article": ".date-outer", "title": ".post-title.entry-title a", "link": ".post-title.entry-title a"}},
|
| 26 |
+
"NVIDIA Developer Blog": {"url": "https://developer.nvidia.com/blog/", "selectors": {"article": "article", "title": "h2 a", "link": "h2 a", "image": "img"}},
|
| 27 |
+
"JetBrains Blog": {"url": "https://blog.jetbrains.com/", "selectors": {"article": ".post-item", "title": ".post-title a", "link": ".post-title a", "image": "img"}},
|
| 28 |
+
"Stack Overflow Blog": {"url": "https://stackoverflow.blog/", "selectors": {"article": ".post", "title": "h2 a", "link": "h2 a", "image": "img"}},
|
| 29 |
+
"OpenAI Blog": {"url": "https://openai.com/research/", "selectors": {"article": ".post", "title": "h3 a", "link": "h3 a", "image": "img"}},
|
| 30 |
+
"MIT Technology Review": {"url": "https://www.technologyreview.com/topic/artificial-intelligence/", "selectors": {"article": ".river__item", "title": "h3 a", "link": "h3 a", "image": "img"}},
|
| 31 |
+
"Android Developers Blog": {"url": "https://android-developers.googleblog.com/", "selectors": {"article": ".post-outer", "title": "h3 a", "link": "h3 a", "image": "img"}},
|
| 32 |
+
"GitHub Trending": {"url": "https://github.com/trending", "selectors": {}}
|
| 33 |
+
}
|
| 34 |
+
|
| 35 |
+
def fetch_page(url):
|
| 36 |
+
"""Fetch HTML page content safely."""
|
| 37 |
+
try:
|
| 38 |
+
response = requests.get(url, timeout=5)
|
| 39 |
+
response.raise_for_status()
|
| 40 |
+
return response.text
|
| 41 |
+
except requests.RequestException:
|
| 42 |
+
return None
|
| 43 |
+
|
| 44 |
+
def scrape_news(source_name, config):
|
| 45 |
+
"""Scrapes news articles from a given source."""
|
| 46 |
+
if source_name == "GitHub Trending":
|
| 47 |
+
return get_github_trending()
|
| 48 |
+
|
| 49 |
+
html = fetch_page(config["url"])
|
| 50 |
+
if not html:
|
| 51 |
+
return []
|
| 52 |
+
|
| 53 |
+
soup = BeautifulSoup(html, "html.parser")
|
| 54 |
+
news_list = []
|
| 55 |
+
|
| 56 |
+
for article in soup.select(config["selectors"]["article"])[:5]: # Get top 5 articles
|
| 57 |
+
title_tag = article.select_one(config["selectors"]["title"])
|
| 58 |
+
link_tag = article.select_one(config["selectors"]["link"])
|
| 59 |
+
img_tag = article.select_one(config["selectors"].get("image", ""))
|
| 60 |
+
|
| 61 |
+
title = title_tag.text.strip() if title_tag else "No Title"
|
| 62 |
+
link = link_tag["href"] if link_tag else "#"
|
| 63 |
+
image = img_tag["src"] if img_tag and "src" in img_tag.attrs else None
|
| 64 |
+
|
| 65 |
+
if "base_url" in config and not link.startswith("http"):
|
| 66 |
+
link = config["base_url"] + link
|
| 67 |
+
|
| 68 |
+
news_list.append({"source": source_name, "title": title, "url": link, "image": image})
|
| 69 |
+
|
| 70 |
+
return news_list
|
| 71 |
+
|
| 72 |
+
def get_github_trending():
|
| 73 |
+
"""Scrapes GitHub trending repositories."""
|
| 74 |
+
url = "https://github.com/trending"
|
| 75 |
+
headers = {"User-Agent": "Mozilla/5.0"}
|
| 76 |
+
|
| 77 |
+
response = requests.get(url, headers=headers)
|
| 78 |
+
if response.status_code != 200:
|
| 79 |
+
return []
|
| 80 |
+
|
| 81 |
+
soup = BeautifulSoup(response.text, "html.parser")
|
| 82 |
+
articles = []
|
| 83 |
+
|
| 84 |
+
for repo in soup.find_all("article", class_="Box-row")[:5]: # Get top 5 trending
|
| 85 |
+
title = repo.find("h2").text.strip().replace("\n", "").replace(" ", "")
|
| 86 |
+
repo_url = "https://github.com" + repo.find("h2").find("a")["href"]
|
| 87 |
+
image = "https://github.githubassets.com/images/modules/logos_page/GitHub-Mark.png"
|
| 88 |
+
|
| 89 |
+
articles.append({"source": "GitHub Trending", "title": title, "url": repo_url, "image": image})
|
| 90 |
+
|
| 91 |
+
return articles
|
| 92 |
+
|
| 93 |
+
@app.route('/news', methods=['GET'])
|
| 94 |
+
def get_coding_news():
|
| 95 |
+
"""Fetches news from random sources and shuffles output."""
|
| 96 |
+
try:
|
| 97 |
+
selected_sources = random.sample(list(NEWS_SOURCES.keys()), 8) # Select 8 random sources
|
| 98 |
+
all_news = []
|
| 99 |
+
|
| 100 |
+
for source in selected_sources:
|
| 101 |
+
all_news.extend(scrape_news(source, NEWS_SOURCES[source]))
|
| 102 |
+
|
| 103 |
+
random.shuffle(all_news) # Shuffle news articles to avoid repetition
|
| 104 |
+
|
| 105 |
+
return jsonify(all_news[:15]) # Limit response to 15 articles
|
| 106 |
+
except Exception as e:
|
| 107 |
+
return jsonify({"error": str(e)}), 500
|
| 108 |
+
|
| 109 |
+
if __name__ == "__main__":
|
| 110 |
+
app.run(host="0.0.0.0", port=7860, debug=True)
|