def writeHeadings():
f = open("all_headings_other_without.txt", 'w')
fileset = getFiles("/home/shreya/Wharton/NEW/Other/ONLY_XML")
for filepath in fileset:
index = filepath.index(".")
if "xml" in filepath[index:]:
print filepath
pt = ParseText(filepath)
content = pt.readXmlToString()
#print content
content_list = pt.readTextToList()
heading_indexes, headings = pt.findHeadings(content, content_list, [])
#print headings
for heading in headings:
f.write(heading.encode('ascii', 'ignore') + "\n")
f.close()
# Change this: should only merge_toplines on lines that had single-letter changes
def preprocess(soup):
soup,s_set = merge_sletters(soup)
print s_set
merge_toplines(soup,s_set)
return soup
# # Extract data from all resumes
#CODE START FROM HERE
fileset = getFiles("/home/shreya/RA_ML/Resume-Parsing/Data/split/Other")
for f_csv in fileset:
index = f_csv.index(".")
first_index =f_csv.rfind("/")+1
last_index = f_csv.rfind(".")
out_filename = f_csv[first_index: last_index]
with open(f_csv, 'rb') as f:
reader = csv.reader(f)
data = [row for row in reader]
datanp = np.array(data)
# print line
value += line + "\n"
"""if k_flag:
print key
"""
if k_flag and v_flag:
print "HERE"
work_exp[key] = value
return work_exp
if __name__ == "__main__":
PROBABLE_HEADINGS = getAllHeadings("set_of_headings.txt")
fileset = getFiles("/home/shreya/Wharton/XML")
with open("work_exp.csv", "w") as csvfile:
csvwriter = csv.writer(csvfile, delimiter=",")
csvwriter.writerow(["Filename", "Company, Position, Duration", "About Job", "EXPERIENCE"])
for xml_filepath in fileset:
index = xml_filepath.index(".")
if "xml" in xml_filepath[index:]:
# print "xml: ", xml_filepath
row = []
first_index = xml_filepath.rfind("/") + 1
last_index = xml_filepath.rfind(".")
filename = xml_filepath[first_index:last_index]
# print "filename: "+filename
text_filepath = "/home/shreya/Wharton/PDF_text/" + filename + ".txt"
# print "text_filepath: ", text_filepath
pt = ParseText(xml_filepath, text_filepath)
#break
return file_year
if __name__ == "__main__":
PROBABLE_HEADINGS = getAllHeadings("set_of_headings_1.txt")
print "OLD LEN: ", len(PROBABLE_HEADINGS)
PROBABLE_HEADINGS.extend(getAllHeadings("set_of_headings_boston.txt"))
PROBABLE_HEADINGS.extend(getAllHeadings("set_of_headings_newyork.txt"))
PROBABLE_HEADINGS.extend(getAllHeadings("set_of_headings_other.txt"))
PROBABLE_HEADINGS = list(set(PROBABLE_HEADINGS))
print "NEW LEN: ", len(PROBABLE_HEADINGS)
if "education:" in PROBABLE_HEADINGS:
print "AYE!"
fileset = getFiles("/home/shreya/Wharton/NEW/Other/ONLY_XML")
fileSet = []
for f in fileset:
if ".xml" == f[-4:]:
fileSet.append(f)
#print len(fileSet)
for i in range(0, len(fileSet), 50):
if (i+50)< len(fileSet):
file_set = fileSet[i: i+50]
else:
file_set = fileSet[i:]
try:
def convertAll(dirpath="", outdir=""): filepaths = getFiles(dirpath) for filepath in filepaths: print filepath if filepath[-4:] == ".pdf": pdfToXML(filepath, outdir)