Check number of recipes on https://en.cookpad.com/

check_cookpad_en.py

#!/usr/bin/env python

import os
import time
import urlparse

import requests
from scrapy.selector import HtmlXPathSelector

def get_count(url):
    r = requests.get(url)
    hxs = HtmlXPathSelector(text=r.text)
    count = int(hxs.select("//h1[@class='title page_title']/span").re('\d+')[0])
    return count

def main():
    urls = [
        'https://en.cookpad.com/categories/vegetables',
        'https://en.cookpad.com/categories/meat',
        'https://en.cookpad.com/categories/fish',
        'https://en.cookpad.com/categories/salad',
        'https://en.cookpad.com/categories/rice',
        'https://en.cookpad.com/categories/noodles',
        'https://en.cookpad.com/categories/pasta-gratin',
        'https://en.cookpad.com/categories/soup-stew',
        'https://en.cookpad.com/categories/bento',
        'https://en.cookpad.com/categories/tofu-soybeans',
        'https://en.cookpad.com/categories/egg',
        'https://en.cookpad.com/categories/flour',
        'https://en.cookpad.com/categories/sauce-dressing',
        'https://en.cookpad.com/categories/healthy-meal',
        'https://en.cookpad.com/categories/party',
        'https://en.cookpad.com/categories/spice-herb',
        'https://en.cookpad.com/categories/yogurt',
        'https://en.cookpad.com/categories/miso-vinegar-fermentation',
        'https://en.cookpad.com/categories/sea-vegetables',
        'https://en.cookpad.com/categories/hot-pot-and-nabe',
        'https://en.cookpad.com/categories/japanese-new-year',
        'https://en.cookpad.com/categories/regional',
        'https://en.cookpad.com/categories/christmas',
        'https://en.cookpad.com/categories/finger%20food',
        'https://en.cookpad.com/categories/bread',
        'https://en.cookpad.com/categories/korokke-croquette',
        'https://en.cookpad.com/categories/chinese',
    ]

    for url in urls:
        count = get_count(url)
        name = os.path.basename(urlparse.urlsplit(url).path)
        print('{0:25s}\t{1}'.format(name, count))
        time.sleep(1)

if __name__ == '__main__':
    main()