def test_content_only_from_obj():
# acquire data from a test html page built in cleanHtme::buildTestHtml
clsObj = CaptureContent()
name = dateFinder.buildTestHtml()
soup = BeautifulSoup(name)
exclude = []
minLength = 10
# we should have one html object with both 'dogma' and 'karma', three with any of these
andOr = "and"
include = ["dogma", "karma"]
content = clsObj.captureContent(soup, include, exclude, minLength=minLength, andOr=andOr)
assert len(content) == 1
andOr = "or"
content = clsObj.captureContent(soup, include, exclude, minLength=minLength, andOr=andOr)
assert len(content) == 3
# we should have three with 'dogma' only, and one if we exclude mentions of 'fang'
include = ["dogma"]
content = clsObj.captureContent(soup, include, exclude, minLength=minLength, andOr=andOr)
assert len(content) == 3
exclude = ["fang"]
content = clsObj.captureContent(soup, include, exclude, minLength=minLength, andOr=andOr)
assert len(content) == 1
# make sure when run from the main routine, the expected information is returned
results = clsObj.capture_main(
name=name, streamType="o", include=include, exclude=exclude, minLength=minLength, andOr=andOr
)
assert len(results["polishedCont"]) == 1
assert len(results["contentAsSoupObjects"]) == 1
assert len(results["metaData"]) == 2
assert len(results["links"]) == 2
def test_main_with_obj():
# acquire data from a test html page built in cleanHtml::buildTestHtml
clsObj = CaptureContent()
name = dateFinder.buildTestHtml()
soup = BeautifulSoup(name)
exclude = []
minLength = 10
streamType = "o"
# we should have one html object with both 'dogma' and 'karma', three with any of these
andOr = "and"
include = ["dogma", "karma"]
clsObj.capture_main(name, streamType, include, exclude, minLength, andOr, socket_timeout=None)
a = 1
