cgiacofei/TandoorRecipes
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Revert "bug fix url import"

Browse Source 
This reverts commit 4ab8ca51e812d02911f4da801767612e52953a23.
This commit is contained in:
smilerz
2021-04-14 09:18:14 -05:00
parent 19e8e5cb5b
commit 0953af05fc
5 changed files with 21 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
cookbook/helper/recipe_html_import.py
View File

@ -76,9 +76,6 @@ 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")
@ -86,8 +83,6 @@ 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)
@ -100,6 +95,15 @@ 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)