bug fix url import

cookbook/helper/recipe_html_import.py

@@ -76,6 +76,9 @@ def get_recipe_from_source(text, url, space):
     text = normalize_string(text)
     try:
         parse_list.append(remove_graph(json.loads(text)))
+        if not url and 'url' in parse_list[0]:
+            url = parse_list[0]['url']
+        scrape = text_scraper("<script type='application/ld+json'>" + text + "</script>", url=url)
 
     except JSONDecodeError:
         soup = BeautifulSoup(text, "html.parser")
@@ -83,6 +86,8 @@ def get_recipe_from_source(text, url, space):
         images += get_images_from_source(soup, url)
         for el in soup.find_all('script', type='application/ld+json'):
             el = remove_graph(el)
+            if not url and 'url' in el:
+                url = el['url']
             if type(el) == list:
                 for le in el:
                     parse_list.append(le)
@@ -95,15 +100,6 @@ def get_recipe_from_source(text, url, space):
                     parse_list.append(le)
             elif type(el) == dict:
                 parse_list.append(el)
-
-    # if a url was not provided, try to find one in the first document
-    if not url and len(parse_list) > 0:
-        if 'url' in parse_list[0]:
-            url = parse_list[0]['url']
-
-    if type(text) == dict:
-        scrape = text_scraper("<script type='application/ld+json'>" + text + "</script>", url=url)
-    elif type(text) == str:
         scrape = text_scraper(text, url=url)
 
     recipe_json = helper.get_from_scraper(scrape, space)

cookbook/helper/recipe_url_import.py

@@ -39,10 +39,9 @@ def get_from_scraper(scrape, space):
             pass
 
     try:
-        recipe_json['image'] = parse_image(scrape.image())
+        recipe_json['image'] = parse_image(scrape.image()) or ''
     except (AttributeError, TypeError):
         recipe_json['image'] = ''
-        pass
 
     keywords = []
     try:
@@ -283,11 +282,11 @@ def parse_keywords(keyword_json, space):
     # keywords as list
     for kw in keyword_json:
         kw = normalize_string(kw)
-        if k := Keyword.objects.filter(name=kw, space=space).first():
+        if len(kw) != 0:
-            if len(k) != 0:
+            if k := Keyword.objects.filter(name=kw, space=space).first():
                 keywords.append({'id': str(k.id), 'text': str(k)})
-        else:
+            else:
-            keywords.append({'id': random.randrange(1111111, 9999999, 1), 'text': kw})
+                keywords.append({'id': random.randrange(1111111, 9999999, 1), 'text': kw})
 
     return keywords
 

cookbook/helper/scrapers/scrapers.py

@@ -30,7 +30,7 @@ def text_scraper(text, url=None):
             url=None
         ):
             self.wild_mode = False
-            self.exception_handling = _exception_handling
+            self.exception_handling = None
             self.meta_http_equiv = False
             self.soup = BeautifulSoup(page_data, "html.parser")
             self.url = url

cookbook/tests/other/_recipes.py

@@ -1705,7 +1705,7 @@ MADAME_DESSERT = {
     "servings": 6,
     "prepTime": 0,
     "cookTime": 20,
-    "image": "https://madamedessert.de/wp-content/uploads/2020/02/Madame-Dessert_Schokopudding-Schokoladenpudding-mit-echter-Schokolade-0238-scaled.jpg",
+    "image": "https://assets.madamedessert.de/wp-content/uploads/2020/02/25163328/Madame-Dessert_Schokopudding-Schokoladenpudding-mit-echter-Schokolade-0238-scaled.jpg",
     "keywords": [
         {
             "id": 7588432,
@@ -1795,7 +1795,7 @@ MADAME_DESSERT = {
             "original": "1 TL Vanilleextrakt"
         },
         {
-            "amount": 125,
+            "amount": 150,
             "unit": {
                 "text": "g",
                 "id": 24254
@@ -1805,7 +1805,7 @@ MADAME_DESSERT = {
                 "id": 42645
             },
             "note": "",
-            "original": "125 g Zucker"
+            "original": "150 g Zucker"
         },
         {
             "amount": 30,