Created
August 7, 2016 13:20
-
-
Save nirmalyaghosh/e31dfcdf36ab6020c35db81af21582d6 to your computer and use it in GitHub Desktop.
Scrapes Google for gathering news summaries. Written in response to http://stackoverflow.com/q/38769951. The code can obviously be improved. It was quickly written to give an idea.
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 bs4 import BeautifulSoup | |
import requests | |
import time | |
from random import randint | |
def scrape_news_summaries(s): | |
# It is based on a notebook posted on Kaggle, http://bit.ly/1VJ8pF9 | |
time.sleep( randint(0,2) ) #relax and don't let google be angry | |
r = requests.get("http://www.google.co.uk/search?q="+s+"&tbm=nws") | |
content = r.text | |
news_summaries = [] | |
soup = BeautifulSoup(content) | |
st_divs = soup.findAll("div", {"class": "st"}) | |
for st_div in st_divs: | |
news_summaries.append(st_div.text) | |
return news_summaries | |
# l = scrape_news_summaries("T-Notes") | |
l = scrape_news_summaries(""""Sovereign-Debt"+Government-Bonds""") | |
for n in l: | |
print n, "\n" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment