mirrors/recipes
1
0
Fork 0
mirror of https://github.com/TandoorRecipes/recipes.git synced 2026-01-09 08:08:24 -05:00
Code Issues Packages Projects Releases Wiki Activity

updated bookmarklet to work with updated import process

Browse Source
This commit is contained in:
smilerz
2021-04-14 11:29:35 -05:00
parent faf458e8ef
commit 018fa0a62f
5 changed files with 24 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
cookbook/helper/recipe_html_import.py
View File

@@ -73,11 +73,9 @@ def get_recipe_from_source(text, url, space):
html_data = []
images = []
# 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")
@@ -85,8 +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)
@@ -99,6 +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)

2
cookbook/helper/scrapers/scrapers.py
View File

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