def downloadXkcd(start_comic, end_comic): for url_number in range(start_comic, end_comic): print(f'{url_number}') r = HTMLSession().get(f'https://xkcd.com/{url_number}') r.raise_for_status() comic = r.html.find('#comic img', first=True) if comic == []: print('Could not find comic image.') else: comic_url = comic.attrs['src'] #print(f'Downloading image {comic_url}...') r = HTMLSession().get('https:' + comic_url) r.raise_for_status() with open(os.path.join('D:\\Ambiente de Trabalho\\pasta', os.path.basename(comic_url)), 'wb') as image_file: image_file.write(r.content)
def fetch_ads(url='http://tankeogteknikk.no/qmedia/oslo.php'): """Crawl tankeogteknikk web site and fetch current ads""" try: r = HTMLSession().get(url) except RequestError: logger.exception('failed to fetch ads') return [] r.raise_for_status() # raise exception if 404 or other non ok http status subs = r.html.find('table.sub') ads = [_parse_sub_advert(sub) for sub in subs] for ad in ads: # use absolute and quoted urls ad['image'] = parse.quote(parse.urljoin(url, ad['image']), safe='/:') return ads