def setUp(self):
self.text = """<root>
<body>
<p>
<p>paragrafo 1</p>
<p>paragrafo 2</p>
</p>
</body>
</root>"""
self.xml = etree.fromstring(self.text)
self.pipe = HTML2SPSPipeline().RemovePWhichIsParentOfPPipe()
def transform_body(self):
for index, body in enumerate(self.xmltree.xpath("//body"), start=1):
logger.info("Processando body numero: %s" % index)
txt_body = body.findtext("./p") or ""
convert = HTML2SPSPipeline(pid=self.publisher_id, index_body=index)
_, obj_html_body = convert.deploy(txt_body)
# sobrecreve o html escapado anterior pelo novo xml tratado
body.getparent().replace(body, obj_html_body.find("body"))
return self.xmltree
def transform_body(self, spy=False):
for index, body in enumerate(self.xmltree.xpath("//body"), start=1):
logger.debug("Processando body numero: %s" % index)
txt_body = body.findtext("./p") or ""
convert = HTML2SPSPipeline(
pid=self.scielo_pid_v2,
ref_items=self._get_ref_items(body),
body_index=index,
spy=spy,
)
_, obj_html_body = convert.deploy(txt_body)
# sobrecreve o html escapado anterior pelo novo xml tratado
if obj_html_body.tag != "body":
obj_html_body = obj_html_body.find("body")
if obj_html_body is None:
raise TypeError("XML: %s esta sem Body" % (self.scielo_pid_v2))
body.getparent().replace(body, obj_html_body)
return self.xmltree
def test_create_instance(self):
expected_text = "<p>La nueva epoca de la revista<italic>Salud Publica de Mexico </italic></p>"
pipeline = HTML2SPSPipeline()
raw, xml = pipeline.SetupPipe().transform(expected_text)
self.assertIn(expected_text, str(etree.tostring(xml)))
def setUp(self):
filename = os.path.join(SAMPLES_PATH, "example_convert_html.xml")
with open(filename, "r") as f:
self.xml_txt = f.read()
self.etreeXML = etree.fromstring(self.xml_txt)
self.pipeline = HTML2SPSPipeline()