robotframework-pdf2textlibrary/build/lib/Pdf2TextLibrary/__init__.py at beaee5556b0396cb774301cf1a097e1b128da682 · qahive/robotframework-pdf2textlibrary · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO

class Pdf2TextLibrary(object):
    ROBOT_LIBRARY_SCOPE = 'Global'

    def __init__(self):
        print('pdf to text library')

    def convert_pdf_to_txt(self,path):
        rsrcmgr = PDFResourceManager()
        retstr = StringIO()
        codec = 'utf-8'
        laparams = LAParams()
        device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
        fp = file(path, 'rb')
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        password = ""
        maxpages = 0
        caching = True
        pagenos=set()
        for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):
            interpreter.process_page(page)
        fp.close()
        device.close()
        str = retstr.getvalue()
        retstr.close()
        return str

    def count_pdf_pages(self,path):
        rsrcmgr = PDFResourceManager()
        retstr = StringIO()
        codec = 'utf-8'
        laparams = LAParams()
        device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
        fp = file(path, 'rb')
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        password = ""
        maxpages = 0
        caching = True
        pagenos=set()
        pagenumber=0
        for page in enumerate(PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True)):
            pagenumber=pagenumber+1
        fp.close()
        device.close()
        return pagenumber