Here's my code, I'm looking for a way to count the images in the pdfs while I extract the text.
import pyPdf
import os
import csv
class UnicodeWriter:
"""
A CSV writer which will write rows to CSV file "f",
which is encoded in the given encoding.
"""
def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
# Redirect output to a queue
self.queue = cStringIO.StringIO()
self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
self.stream = f
self.encoder = codecs.getincrementalencoder(encoding)()
def writerow(self, row):
self.writer.writerow([s.encode("utf-8") for s in row])
# Fetch UTF-8 output from the queue ...
data = self.queue.getvalue()
data = data.decode("utf-8")
# ... and reencode it into the target encoding
data = self.encoder.encode(data)
# write to the target stream
self.stream.write(data)
# empty queue
self.queue.truncate(0)
def writerows(self, rows):
for row in rows:
self.writerow(row)
PDFWriter = csv.writer(open('/home/nick/TAM_work/text/text.csv', 'a'), delimiter=' ', quotechar='|', quoting=csv.QUOTE_ALL) #assigns PDFWriter and tells it to append the existing file so many PDF's can be entered (in order as well). Also tells it what to take.
def getPDFContent(path):
content = ""
# Load PDF into pyPDF
pdf = pyPdf.PdfFileReader(file(path, "rb"))
# Iterate pages
for i in range(0, pdf.getNumPages()):
# Extract text from page and add to content
content += pdf.getPage(i).extractText() + "\n"
# Collapse whitespace
content = " ".join(content.replace(u"\xa0", " ").strip().split())
return content
for word in os.listdir("/home/nick/TAM_work/TAM_pdfs"):
print getPDFContent("/home/nick/TAM_work/TAM_pdfs/" + word)
PDFWriter.writerow ([getPDFContent("/home/nick/TAM_work/TAM_pdfs/" + word).encode("ascii", "ignore")]) #applies getPDFContent to all objects in os.listdir and after printing into the terminal renders and saves text in CSV file. .encode... takes out a error that is raised that terminates the program.
I'd love any help, Thanks, Matt