pettr.py

import re
import requests
from lxml import html

rspca_base = 'https://www.rspca.org.uk'

def get_pet(name, ref):
    base = rspca_base + '/findapet/details/-/Animal/{0}/ref/{1}/rehome/'
    base = base.format(name, ref)
    r = requests.get(base)
    tree = html.fromstring(r.content)

    overview = tree.xpath("//div[@class='petOverview']")[0]

    main_image = None
    e = tree.xpath("//img[@id='largeImage']")
    if len(e) > 0:
        main_image = e[0].get('src')

    pet_type = None
    breed = None
    colour = None
    age = None

    at_a_glance = overview.xpath("//div[@class='atAGlance']")[0]
    for e in at_a_glance:
        m = re.search('Type: (.*)', e.text_content())
        if m is not None:
            pet_type = m.group(1).strip()

        m = re.search('Breed: (.*)', e.text_content())
        if m is not None:
            breed = m.group(1).strip()

        m = re.search('Colour: (.*)', e.text_content())
        if m is not None:
            colour = m.group(1).strip()

        m = re.search('Age: (.*)', e.text_content())
        if m is not None:
            age = m.group(1).strip()

    description = None

    data = {
        "name": name,
        "ref": ref,
        "main_image": main_image,
        "breed": breed,
        "colour": colour,
        "age": age,
        "description": description
    }

    return data

pet = get_pet('DAKOTA', 'BSA2038947')