elif elem.tag in ["{http://www.tei-c.org/ns/1.0}head", "{http://www.tei-c.org/ns/1.0}p"]:
full_text_bits.extend([self._extract_text(elem), "\n"])
elif elem.tag=="{http://www.tei-c.org/ns/1.0}author" and "{http://www.tei-c.org/ns/1.0}fileDesc" in path:
author_list.append(re.sub("\s+"," ", self._extract_text(elem)))
path.pop()
After Change
elif elem.tag in ["{http://www.tei-c.org/ns/1.0}head", "{http://www.tei-c.org/ns/1.0}p"]:
full_text_bits.extend([self._extract_text(elem), "\n"])
elif elem.tag=="{http://www.tei-c.org/ns/1.0}persName" and "{http://www.tei-c.org/ns/1.0}fileDesc" in path:
forenames = [e.text for e in elem.findall("{http://www.tei-c.org/ns/1.0}forename")]
lastnames = [e.text for e in elem.findall("{http://www.tei-c.org/ns/1.0}surname")]
initials = [f[0] for f in forenames]
// NB the format below is identical to that used in pubmed_robot.py
author_list.append({"initials": u"".join(initials),
"forename": u" ".join(forenames),
"lastname": u" ".join(lastnames)})
