def doc_path_to_dict(path):
directory, fname = os.path.split(path)
reader = XMLCorpusReader(directory, fname)
doc = reader.xml()
try:
return process_doc(doc)
except ValueError, e:
return e.args[0]
'paul krugman', 'maureen dowd', 'frank rich', 'verlyn klinkenborg',
'adam cohen', 'lawrence downes'
]
roottest = './nyt_corpus/data/2005/**/**/'
nottestmode = False
authord = defaultdict(list)
icount = 0
ncount = 0
acount = 0
for filename in texts:
reader = XMLCorpusReader(os.path.dirname(filename),
os.path.basename(filename))
xml = reader.xml()
ptext = ""
desk = ""
body = xml.find('body')
head = xml.find('head')
auth = body.find('body.head').find('byline')
for d in head:
if d.get("name") == "dsk":
desk = d.get("content")
if desk == "Editorial Desk":
icount += 1
try:
if auth is not None:
auth = auth.text
if auth is not None:
acount += 1
