use this function to get the wiki extract working.

[grahamwaters]

HowTimeFlies/scripts/01_getimages_google_imagesearch.py

Lines 59 to 117 in b7beeca

	print("wikipedia extraction for the year...")
	saved_folder = f'Wiki_images/{this_year}'
	if not os.path.exists(saved_folder):
	os.mkdir(saved_folder)
	try:
	iterations = download_wiki_images(this_year,saved_folder,iterations)
	except Exception as e:
	print("error with wikipedia data pull")
	print(e)
	"""
	def download_wiki_images(this_year, saved_folder, iterations):
	aspect_one = this_year
	iterations = iterations + 1
	if iterations % 20 == 0:
	time.sleep(15)
	wikipedia_image = (
	f"https://commons.wikimedia.org/wiki/Category:{str(this_year)}_photographs"
	)
	print("\n", wikipedia_image)
	response = requests.get(wikipedia_image, headers=user_agent)
	# print(response)
	html = response.text
	soup = BeautifulSoup(html, "html.parser")
	results = soup.findAll("div", {"class": "gallerytext"})
	count = 1
	links = []
	for result in results:
	try:
	link = result["data-src"]
	links.append(link)
	count += 1
	if count > n_images:
	break
	except KeyError:
	continue
	# totals = totals + len(links)
	print(f"Downloading {len(links)} images...")
	for i, link in enumerate(links):
	response = requests.get(link)
	image_name = saved_folder + "/" + data + str(i + 1) + ".jpg"
	with open(image_name, "wb") as fh:
	fh.write(response.content)
	# print(f'Running total of collected images:{totals}')
	return iterations
	def download_images(