def test_open_file():
with open(os.path.join(TEST_DIR, 'empty.html')) as f:
p = Parser(doc=f)
assert_true(p.__doc__ is not None)
assert_true(type(p) is not None)
assert_true(type(p.to_dict()) is dict)
def test_person_with_url():
p = Parser(doc=open("test/examples/person_with_url.html"))
result = p.to_dict()
assert_equal(result["items"][0]["properties"]["name"],
['Tom Morris'])
assert_equal(result["items"][0]["properties"]["url"],
['http://tommorris.org/'])
def test_person_with_url():
p = Parser(doc=open("test/examples/person_with_url.html"))
result = p.to_dict()
assert_equal(result["items"][0]["properties"]["name"],
['Tom Morris'])
assert_equal(result["items"][0]["properties"]["url"],
['http://tommorris.org/'])
def parse():
if request.method == 'GET':
u = request.args['url']
else:
u = request.form['url']
print(u)
p = Parser(url=unicode(u))
return Response(p.to_json(pretty_print=True), status=200,
mimetype='application/json')
def parse():
if request.method == 'GET':
u = request.args['url']
else:
u = request.form['url']
print(u)
p = Parser(url=unicode(u))
return Response(p.to_json(pretty_print=True),
status=200,
mimetype='application/json')
def test_doc_tag():
# test that strings, BS doc and BS tags are all parsed
doc = '''<article class="h-entry"></article>'''
soup = BeautifulSoup(doc)
parse_string = Parser(doc).to_dict()
assert 'h-entry' in parse_string['items'][0]['type']
parse_doc = Parser(soup).to_dict()
assert 'h-entry' in parse_doc['items'][0]['type']
parse_tag = Parser(soup.article).to_dict()
assert 'h-entry' in parse_tag['items'][0]['type']
def test_photo_with_alt():
"""Confirm that alt text in img is parsed with feature flag img_with_alt under as a u-* property and implied photo
"""
path = 'experimental/img_with_alt.html'
# without flag
result = parse_fixture(path)
# experimental img_with_alt=True
with open(os.path.join(TEST_DIR, path)) as f:
exp_result = Parser(doc=f, html_parser='html5lib', img_with_alt=True).to_dict()
# simple img with u-*
assert_equal('/photo.jpg', result['items'][0]['properties']['photo'][0])
assert_equal('/photo.jpg', exp_result['items'][0]['properties']['photo'][0])
assert_equal('/photo.jpg', result['items'][1]['properties']['url'][0])
assert_equal('/photo.jpg', exp_result['items'][1]['properties']['url'][0]['value'])
assert_equal('alt text', exp_result['items'][1]['properties']['url'][0]['alt'])
assert_equal('/photo.jpg', result['items'][2]['properties']['in-reply-to'][0])
assert_equal('/photo.jpg', exp_result['items'][2]['properties']['in-reply-to'][0]['value'])
assert_equal('', exp_result['items'][2]['properties']['in-reply-to'][0]['alt'])
# img with u-* and h-* example
assert_true('h-cite' in result['items'][3]['properties']['in-reply-to'][0]['type'])
assert_equal('/photo.jpg', result['items'][3]['properties']['in-reply-to'][0]['properties']['photo'][0])
assert_equal('/photo.jpg', result['items'][3]['properties']['in-reply-to'][0]['value'])
assert_false('alt' in result['items'][3]['properties']['in-reply-to'][0])
assert_true('h-cite' in exp_result['items'][3]['properties']['in-reply-to'][0]['type'])
assert_equal('/photo.jpg', exp_result['items'][3]['properties']['in-reply-to'][0]['properties']['photo'][0])
assert_equal('/photo.jpg', exp_result['items'][3]['properties']['in-reply-to'][0]['value'])
assert_false('alt' in exp_result['items'][3]['properties']['in-reply-to'][0])
assert_true('h-cite' in result['items'][4]['properties']['in-reply-to'][0]['type'])
assert_equal('/photo.jpg', result['items'][4]['properties']['in-reply-to'][0]['properties']['photo'][0])
assert_equal('/photo.jpg', result['items'][4]['properties']['in-reply-to'][0]['value'])
assert_false('alt' in result['items'][4]['properties']['in-reply-to'][0])
assert_true('h-cite' in exp_result['items'][4]['properties']['in-reply-to'][0]['type'])
assert_equal('/photo.jpg', exp_result['items'][4]['properties']['in-reply-to'][0]['properties']['photo'][0]['value'])
assert_equal('/photo.jpg', exp_result['items'][4]['properties']['in-reply-to'][0]['value'])
assert_equal('alt text', exp_result['items'][4]['properties']['in-reply-to'][0]['properties']['photo'][0]['alt'])
assert_equal('alt text', exp_result['items'][4]['properties']['in-reply-to'][0]['alt'])
assert_true('h-cite' in result['items'][5]['properties']['in-reply-to'][0]['type'])
assert_equal('/photo.jpg', result['items'][5]['properties']['in-reply-to'][0]['properties']['photo'][0])
assert_equal('/photo.jpg', result['items'][5]['properties']['in-reply-to'][0]['value'])
assert_false('alt' in result['items'][5]['properties']['in-reply-to'][0])
assert_true('h-cite' in exp_result['items'][5]['properties']['in-reply-to'][0]['type'])
assert_equal('/photo.jpg', exp_result['items'][5]['properties']['in-reply-to'][0]['properties']['photo'][0]['value'])
assert_equal('/photo.jpg', exp_result['items'][5]['properties']['in-reply-to'][0]['value'])
assert_equal('', exp_result['items'][5]['properties']['in-reply-to'][0]['properties']['photo'][0]['alt'])
assert_equal('', exp_result['items'][5]['properties']['in-reply-to'][0]['alt'])
def test_input_tree_integrity():
""" make sure that if we parse a BS4 soup, our modifications do not leak into the document represented by it """
for path in get_all_files():
with open(os.path.join(TEST_DIR, path)) as f:
soup = BeautifulSoup(f,features='lxml')
html1 = soup.prettify()
p = Parser(doc=soup, html_parser='lxml')
html2 = soup.prettify()
yield make_labelled_cmp("tree_integrity_" + path), html1, html2
def test_user_agent(getter):
ua_expect = 'mf2py - microformats2 parser for python'
assert_true(Parser.useragent.startswith(ua_expect))
resp = mock.MagicMock()
resp.content = b''
resp.text = ''
resp.headers = {}
getter.return_value = resp
Parser(url='http://example.com')
getter.assert_called_with('http://example.com',
headers={'User-Agent': Parser.useragent})
Parser.useragent = 'something else'
assert_equal(Parser.useragent, 'something else')
# set back to default. damn stateful classes
Parser.useragent = 'mf2py - microformats2 parser for python'
def test_doc_tag_backcompat():
# test that strings, BS doc and BS tags are all parsed and in the latter cases copies are made and are modified by backcompat
doc = '''<article class="hentry"></article>'''
soup = BeautifulSoup(doc)
parse_string = Parser(doc).to_dict()
assert_true('h-entry' in parse_string['items'][0]['type'])
p = Parser(soup)
assert_true('h-entry' in p.to_dict()['items'][0]['type'])
assert_false(soup is p.__doc__)
assert_false(soup == p.__doc__)
p = Parser(soup.article)
assert_true('h-entry' in p.to_dict()['items'][0]['type'])
assert_false(soup.article is p.__doc__)
assert_false(soup.article == p.__doc__)
def test_implied_name_empty_alt():
"""An empty alt text should not prevent us from including other
children in the implied name.
"""
p = Parser(doc="""
<a class="h-card" href="https://twitter.com/kylewmahan">
<img src="https://example.org/test.jpg" alt="">
@kylewmahan
</a>""").to_dict()
hcard = p['items'][0]
assert_equal({
'type': ['h-card'],
'properties': {
'name': ['@kylewmahan'],
'url': ['https://twitter.com/kylewmahan'],
'photo': ['https://example.org/test.jpg'],
},
}, hcard)
def test_complex_e_content():
"""When parsing h-* e-* properties, we should fold {"value":..., "html":...}
into the parsed microformat object, instead of nesting it under an
unnecessary second layer of "value":
"""
result = Parser(doc="""<!DOCTYPE html><div class="h-entry">
<div class="h-card e-content"><p>Hello</p></div></div>""").to_dict()
assert_equal({
"type": ["h-entry"],
"properties": {
"content": [{
"type": [
"h-card"
],
"properties": {
"name": ["Hello"]
},
"html": "<p>Hello</p>",
"value": "Hello"
}],
"name": ["Hello"]
}
}, result["items"][0])
def parse_fixture(path, url=None):
with open(os.path.join("test/examples/", path)) as f:
p = Parser(doc=f, url=url, html_parser='html5lib')
return p.to_dict()
def test_base():
with open(os.path.join(TEST_DIR, 'base.html')) as f:
p = Parser(doc=f)
assert_equal(p.__url__, "http://tantek.com/")
def test_base():
p = Parser(doc=open("test/examples/base.html"))
assert_equal(p.__url__, "http://tantek.com/")
def test_empty():
p = Parser()
assert_true(type(p) is not None)
assert_true(type(p.to_dict()) is dict)
def parse_fixture(path, url=None):
with open(os.path.join(TEST_DIR, path)) as f:
p = Parser(doc=f, url=url, html_parser='html5lib')
return p.to_dict()
def test_simple_person_reference_implied():
p = Parser(doc=open("test/examples/simple_person_reference_implied.html"))
result = p.to_dict()
assert_equal(result["items"][0]["properties"],
{'name': ['Frances Berriman']})
# coding: utf-8
from mf2py import Parser
import os.path
import glob
import json
allfiles = glob.glob(os.path.join('.', 'tests', 'tests', '**', '**', '*.json'))
for jsonfile in allfiles:
htmlfile = jsonfile[:-4] + 'html'
with open(htmlfile) as f:
p = json.loads(Parser(doc=f).to_json(pretty_print=True))
def test_open_file():
p = Parser(doc=open("test/examples/empty.html"))
assert_true(p.__doc__ is not None)
assert_true(type(p) is not None)
assert_true(type(p.to_dict()) is dict)
def test_simple_person_reference_implied():
p = Parser(doc=open("test/examples/simple_person_reference_implied.html"))
result = p.to_dict()
assert_equal(result["items"][0]["properties"],
{'name': ['Frances Berriman']})
def test_open_file():
p = Parser(doc=open("test/examples/empty.html"))
assert_true(p.__doc__ is not None)
assert_true(type(p) is not None)
assert_true(type(p.to_dict()) is dict)
def parse_fixture(path, url=None):
with open(os.path.join("test/examples/", path)) as f:
p = Parser(doc=f, url=url, html_parser='html5lib')
return p.to_dict()