top_instagram_hashtags_crawler

requirements.txt

requests==2.18.4
BeautifulSoup4==4.6.0
lxml==3.8.0

top_instagram_hashtags_crawler.py

import requests
from bs4 import BeautifulSoup
import re


def crawl(max_pages):
    page = 0
    while page < max_pages:
        url = 'https://top-hashtags.com/instagram/' + str(page * 100 + 1) + '/'
        response = requests.get(url)
        soup = BeautifulSoup(response.text, 'lxml')

        for tagLink in soup.select('div.tht-tag > a'):
            tag_string = tagLink.string[1:]
            if not re.match('[가-힣]+', tag_string):
                continue
            if '그램' in tag_string:
                continue
            print(tag_string)
        page += 1

crawl(1000)