Created
May 18, 2015 16:12
-
-
Save dreyco676/56368e85898fc15be637 to your computer and use it in GitHub Desktop.
Python We Follow Scraper
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
import requests | |
from bs4 import BeautifulSoup | |
# Get top influencers from WeFollow | |
def get_influencers(topic, min_rank, max_rank): | |
url = 'http://wefollow.com/interest/' | |
req_url = url + topic + '/' + str(min_rank) + '-' + str(max_rank) | |
response = requests.get(req_url) | |
soup = BeautifulSoup(response.content) | |
# get the blocks of html that contain the information we care about | |
influencer_soup = soup.findAll("div", {"class": "interest-list-user" }) | |
topic_influencers = [] | |
for influencer in influencer_soup: | |
handle = influencer.findAll("p", {"class": "user-username"})[0].string | |
rank = influencer.findAll("p", {"class": "rank-big"})[0].string | |
topic_influencers.append((topic, handle, rank)) | |
return topic_influencers | |
# example | |
# print(get_influencers('hadoop',80,100)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment