scrap-instagram

main.py

"""
Scrap caption and images from instagram using https://deskgram.org 
"""
import requests
from bs4 import BeautifulSoup

BASE_URL = 'https://deskgram.org'
USER = 'healthymealsberlin'

start_url = BASE_URL + '/' + USER

r = requests.get(start_url)
soup = BeautifulSoup(r.text, 'html.parser')
captions = soup.findAll("div", {"class": "post-caption"})
images = soup.findAll("div", {"class": "post-img"})

has_next = True
print ('Found {0} captions.'.format(len(captions)))
print ('Found {0} images.'.format(len(images)))

while True:
    links = soup.findAll('a')
    next_link = list(filter( lambda x: 'next_id' in x['href'], links))
    if len(next_link) == 0:
        break
    else:
        dest = next_link[0]['href']
        next_url = BASE_URL + dest
        print ('fetching {0}'.format(next_url))
        r = requests.get(next_url)
        soup = BeautifulSoup(r.text, 'html.parser')
        captions = soup.findAll("div", {"class": "post-caption"})
        images = soup.findAll("div", {"class": "post-img"})
        print ('Found {0} captions.'.format(len(captions)))
        print ('Found {0} images.'.format(len(images)))