mirrors/recipes
1
0
Fork 0
mirror of https://github.com/TandoorRecipes/recipes.git synced 2026-01-03 05:11:31 -05:00
Code Issues Packages Projects Releases Wiki Activity

Squashed commit of the following:

Browse Source 
commit 707d862e01a7497a1f22879d314b865a35e0e85b
Author: smilerz <smilerz@gmail.com>
Date:   Wed Apr 14 10:35:00 2021 -0500

    works now

commit 3942a445ed4f2ccec57de25eacd86ea4e4dd6bdb
Author: smilerz <smilerz@gmail.com>
Date:   Wed Apr 14 10:25:24 2021 -0500

    updated serializer and api

commit 10dc746eb175c7f805a8a8ffa7ce49977a7ce97e
Author: smilerz <smilerz@gmail.com>
Date:   Wed Apr 14 10:20:19 2021 -0500

    fixed bookmarklet

commit 9779104902d3be0258c95cd2eeebcba0d5d48892
Merge: bb8262c 0cb3928
Author: smilerz <smilerz@gmail.com>
Date:   Wed Apr 14 09:56:27 2021 -0500

    Merge branch 'bookmarklet' into json_import

commit 0cb39284bb835ffc6cfee3e4306aadc4a64a25be
Author: smilerz <smilerz@gmail.com>
Date:   Wed Apr 14 09:42:53 2021 -0500

    retrieve bookmarklet ID from get

commit e89e0218de684d40b2e2bfb6ba833891206c828e
Author: smilerz <smilerz@gmail.com>
Date:   Wed Apr 14 09:29:33 2021 -0500

    Revert "fixed broken tab"

    This reverts commit ca0a1aede3cc6cb3912bc1fe30c0aa22e3f481a6.

commit bb8262ccabb93c56fbc18c407d5a0653b8b3ca79
Merge: b1e73aa 35a7f62
Author: smilerz <smilerz@gmail.com>
Date:   Sun Apr 11 20:35:57 2021 -0500

    Merge branch 'main_fork' into json_import
This commit is contained in:
smilerz
2021-04-14 10:35:52 -05:00
parent 2c5348fcb4
commit faf458e8ef
17 changed files with 84 additions and 445 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
cookbook/helper/recipe_html_import.py
View File

@@ -73,9 +73,11 @@ 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")
@@ -83,6 +85,8 @@ 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 +99,6 @@ 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)

14
cookbook/helper/recipe_url_import.py
View File

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

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 = _exception_handling
self.exception_handling = None
self.meta_http_equiv = False
self.soup = BeautifulSoup(page_data, "html.parser")
self.url = url