Merge branch 'main' of gitlab.constantvzw.org:anais_berck/rewilding-specimens

scripts/scrape_screenshots.py

@@ -0,0 +1,39 @@
+import csv
+from selenium import webdriver
+from time import sleep
+from webdriver_manager.chrome import ChromeDriverManager
+
+# declare driver
+driver = webdriver.Chrome(ChromeDriverManager().install())
+
+# get data
+urls = []
+names = []
+with open("describers_short_long.csv", 'r') as source:
+	csv_reader = csv.DictReader(source)
+	for each_row in csv_reader:
+		name = each_row["Short"]
+		names.append(name)
+		url_wikipedia = each_row["Wikipedia"]
+		urls.append(url_wikipedia)
+
+# get screenshots, with 30 seconds break after 7 requests
+rounds = 0
+position = 0
+for url in urls:
+	print('url:', url)
+	name = names[position]
+	filename = name+".png"
+	print('filename:', filename)
+	driver.get(url)
+	sleep(3)
+	driver.get_screenshot_as_file(filename)
+	sleep(3)
+	position +=1
+	rounds += 1
+	if rounds == 5:
+		sleep(60)
+		rounds == 0
+
+driver.quit()
+print("end...")