scraper for facet.la

facetla_scraper.py

import requests
import shutil
from bs4 import BeautifulSoup

BASE_URL = "http://www.facet.la/wallpapers/"

r = requests.get(BASE_URL)
soup = BeautifulSoup(r.text)

# Loop through all images on the base thumbnail site
for thumb in soup.find_all("div", {"class" : "thumb-image"}):
    # Follow each link and find the wallpaper url
    img = requests.get(thumb.find("a")["href"])
    s = BeautifulSoup(img.text)
    wp_url = s.find("div", {"id" : "facet-image"}).find("img")["src"]

    # Name our image
    wp_name = wp_url.split('/')[-1]
    print("Downloading {0}".format(wp_name))

    # Download the image
    response = requests.get(wp_url, stream=True)
    with open(wp_name, 'wb') as out_file:
        shutil.copyfileobj(response.raw, out_file)
    del response