Télécharger les images d'un contenu

#!/usr/bin/env python

import sys
from urllib.parse import urljoin

import lxml.html
import requests


def find_images_page(page_url, cookies):
    req = requests.get(page_url, cookies=cookies)
    doc = lxml.html.fromstring(req.text)

    img_links = doc.xpath('//div[contains(@class, "gallery-item")]//a')
    images = {}
    for img_link in img_links:
        img_src, = img_link.xpath('.//img/@src')
        img_src, _, _ = img_src.rsplit('.', 2)
        img_src = urljoin(page_url, img_src)
        img_name, = img_link.xpath('.//span[@class="topic-title"]/text()')
        img_edit_link = urljoin(page_url, img_link.get('href'))
        images[img_src] = img_name, img_edit_link

    try:
        rel_next_url, = doc.xpath('(//a[@rel="next"]/@href)[1]')
        next_url = urljoin(page_url, rel_next_url)
    except ValueError:
        next_url = None

    return next_url, images


def iter_gallery_images(gallery_url, cookies):
    next_url = gallery_url
    while next_url is not None:
        next_url, images = find_images_page(next_url, cookies)
        for img_src, (img_name, edit_link) in images.items():
            yield img_src, img_name, edit_link


if __name__ == '__main__':
    if len(sys.argv) < 3:
        print(f'Usage: {sys.argv[0]} gallery_url session_id', file=sys.stderr)
        sys.exit(1)

    _, gallery_url, session_id, *_ = sys.argv

    if not gallery_url.startswith('https://zestedesavoir.com/galerie/'):
        print(f'Malformatted gallery URL', file=sys.stderr)
        sys.exit(1)

    cookies = {'sessionid': session_id}

    for img in iter_gallery_images(gallery_url, cookies):
        print(img)