mirrors/recipes
1
0
Fork 0
mirror of https://github.com/TandoorRecipes/recipes.git synced 2026-01-10 08:38:34 -05:00
Code Issues Packages Projects Releases Wiki Activity

bug fix url import

Browse Source
This commit is contained in:
smilerz
2021-04-06 10:57:13 -05:00
parent 7c682ebab3
commit 6de128757f
5 changed files with 23 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
cookbook/helper/recipe_html_import.py
View File

@@ -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)