Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[MRG+2] Fix: scrapinghub/extruct#84 try to parse JSON-LD with control characters #85

Merged
merged 10 commits into from
Aug 8, 2018
Merged

[MRG+2] Fix: scrapinghub/extruct#84 try to parse JSON-LD with control characters #85

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
ddb25ae
Fix: scrapinghub/extruct#84 try to parse JSON-LD with control charact…
Jul 31, 2018
3b36247
Fix: A typo.
Aug 1, 2018
00d1796
Fix: Make expected list in tests in order to be aligned with `mf2py`.
Aug 1, 2018
af34117
Add: Add test for JSON-LD data with control characters.
Aug 1, 2018
2869a02
Fix: Make tests pass, `json.JSONDecodeError` is only available for Py…
Aug 1, 2018
b95cdc8
Mod: Use `ValueError` again since `json.JSONDecodeError` exists from …
Aug 1, 2018
d1e64b8
Mod: Remove leading comments and allow control characters directly.
Aug 2, 2018
1874473
Mod: Make comment removal a fallback when failed.
Aug 3, 2018
e3b0c4a
Add: Add test for comment, control characters individually and together.
Aug 6, 2018
d839faa
Mod: Make each test for a single and simple case.
shiquanwang Aug 6, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions extruct/jsonld.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,10 +30,11 @@ def extract_items(self, document, base_url=None):
def _extract_items(self, node):
script = node.xpath('string()')
try:
data = json.loads(script)
# TODO: `strict=False` can be configurable if needed
data = json.loads(script, strict=False)
except ValueError:
# sometimes JSON-decoding errors are due to leading HTML or JavaScript comments
data = json.loads(HTML_OR_JS_COMMENTLINE.sub('', script))
data = json.loads(HTML_OR_JS_COMMENTLINE.sub('', script), strict=False)
if isinstance(data, list):
return data
elif isinstance(data, dict):
Expand Down
17 changes: 17 additions & 0 deletions tests/samples/custom.invalid/JSONLD_with_control_characters.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
<!DOCTYPE html>
<html lang="en">

<head>
<script type="application/ld+json">
{
"data": "line 1
line 2
line 3
"
}
</script>
</head>

<body></body>

</html>
5 changes: 5 additions & 0 deletions tests/samples/custom.invalid/JSONLD_with_control_characters.jsonld
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
[
{
"data": "line 1\n line 2\n line 3\n"
}
]
15 changes: 15 additions & 0 deletions tests/samples/custom.invalid/JSONLD_with_control_characters_comment.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
<!DOCTYPE html>
<html lang="en">

<head>
<script type="application/ld+json">
{
"data": "<!-- John joined the festival. --><b>some
text</b>"
}
</script>
</head>

<body></body>

</html>
5 changes: 5 additions & 0 deletions tests/samples/custom.invalid/JSONLD_with_control_characters_comment.jsonld
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
[
{
"data": "<!-- John joined the festival. --><b>some\n text</b>"
}
]
10 changes: 5 additions & 5 deletions tests/samples/misc/microformat_flat_test.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
[
{
"@type": [
"h-hidden-tablet",
"h-hidden-phone"
"h-hidden-phone",
"h-hidden-tablet"
],
"name": [
""
Expand All @@ -17,8 +17,8 @@
"children": [
{
"@type": [
"h-hidden-tablet",
"h-hidden-phone"
"h-hidden-phone",
"h-hidden-tablet"
],
"name": [
""
Expand Down Expand Up @@ -72,4 +72,4 @@
"2013-06-13 12:00:00"
]
}
]
]
10 changes: 5 additions & 5 deletions tests/samples/misc/microformat_test.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,8 +6,8 @@
]
},
"type": [
"h-hidden-tablet",
"h-hidden-phone"
"h-hidden-phone",
"h-hidden-tablet"
]
},
{
Expand All @@ -20,8 +20,8 @@
]
},
"type": [
"h-hidden-tablet",
"h-hidden-phone"
"h-hidden-phone",
"h-hidden-tablet"
]
},
{
Expand Down Expand Up @@ -80,4 +80,4 @@
"h-entry"
]
}
]
]
19 changes: 19 additions & 0 deletions tests/test_jsonld.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@
from extruct.jsonld import JsonLdExtractor
from tests import get_testdata


class TestJsonLD(unittest.TestCase):

def test_schemaorg_CreativeWork(self):
Expand Down Expand Up @@ -42,3 +43,21 @@ def test_jsonld_with_comments(self):
jsonlde = JsonLdExtractor()
data = jsonlde.extract(body)
self.assertEqual(data, expected)

def test_jsonld_with_control_characters(self):
page = 'JSONLD_with_control_characters'
body = get_testdata('custom.invalid', '{}.html'.format(page))
expected = json.loads(get_testdata('custom.invalid', '{}.jsonld'.format(page)).decode('UTF-8'))

jsonlde = JsonLdExtractor()
data = jsonlde.extract(body)
self.assertEqual(data, expected)

def test_jsonld_with_control_characters_comment(self):
page = 'JSONLD_with_control_characters_comment'
body = get_testdata('custom.invalid', '{}.html'.format(page))
expected = json.loads(get_testdata('custom.invalid', '{}.jsonld'.format(page)).decode('UTF-8'))

jsonlde = JsonLdExtractor()
data = jsonlde.extract(body)
self.assertEqual(data, expected)
6 changes: 3 additions & 3 deletions tests/test_uniform.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,12 +29,12 @@ def test_uopengraph(self):

def test_umicroformat(self):
expected = [ { '@context': 'http://microformats.org/wiki/',
'@type': ['h-hidden-tablet', 'h-hidden-phone'],
'@type': ['h-hidden-phone', 'h-hidden-tablet'],
'name': ['']},
{ '@context': 'http://microformats.org/wiki/',
'@type': ['h-hidden-phone'],
'children': [ { '@type': [ 'h-hidden-tablet',
'h-hidden-phone'],
'children': [ { '@type': [ 'h-hidden-phone',
'h-hidden-tablet'],
'name': ['']},
{ '@type': ['h-hidden-phone'],
'name': [ 'aJ Styles FastLane 2018 15 x '
Expand Down