Initial commit

birdscrape.py

@@ -0,0 +1,56 @@
+import requests
+import shutil
+
+from bs4 import BeautifulSoup
+
+def downloadImage(url, filename):
+    # Open the url image, set stream to True, this will return the stream content.
+    r = requests.get(url, stream = True)
+
+    # Check if the image was retrieved successfully
+    if r.status_code == 200:
+        # Set decode_content value to True, otherwise the downloaded image file's size will be zero.
+        r.raw.decode_content = True
+        
+        # Open a local file with wb ( write binary ) permission.
+        with open(filename,'wb') as f:
+            shutil.copyfileobj(r.raw, f)
+            
+        print('Image sucessfully Downloaded: ',filename)
+    else:
+        print('Image Couldn\'t be retreived')    
+
+URL = "http://tirill.de/illustrierte-voegel-liste.html"
+html_text = requests.get(URL)
+soup = BeautifulSoup(html_text.text, 'html.parser')
+
+# Dictionary for all bird URLs
+bird_dict_urls = {"URL":[]}
+
+birdlist = soup.find('ul', class_ = "level_1")
+
+print("Getting list of all illustrated birds on: " + URL)
+
+for bird in birdlist.findAll('li'):
+    bird_url = "http://tirill.de/" + bird.a['href']
+    #print(bird_url)
+    bird_dict_urls["URL"].append(bird_url)
+    
+print(str(len(bird_dict_urls["URL"])) + " Vochels gefunden.")
+
+for i in bird_dict_urls["URL"]:
+    ## SING BIRD INFO + DOWNLOAD
+    html_bird = requests.get(i)
+    bird_soup = BeautifulSoup(html_bird.text, 'html.parser')
+
+    bird_images_container = bird_soup.find_all('figure', class_ = "image_container")
+    #print(bird_images_container)
+
+    for image in bird_images_container:
+        #print(image.img['alt'])
+        #print(image.img['src'])
+        full_path_img = "https://tirill.de/" + image.img['src']
+        filename = full_path_img.split("/")[-1]
+        print(full_path_img)
+        print(filename)
+        downloadImage(full_path_img, filename)