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

bring parser inline with json_import branch

Browse Source
This commit is contained in:
smilerz
2021-04-15 09:57:10 -05:00
parent 25f6adba1f
commit a701437548
2 changed files with 21 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
cookbook/helper/recipe_html_import.py
View File

@@ -68,7 +68,7 @@ def get_recipe_from_source(text, url, space):
'servings': '',
'prepTime': '',
'cookTime': ''
}
}
recipe_tree = []
parse_list = []
html_data = []
@@ -77,6 +77,9 @@ def get_recipe_from_source(text, url, space):
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")
@@ -84,6 +87,8 @@ 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)
@@ -96,15 +101,6 @@ 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)