Как удалить UnicodeEncodeError при использовании HTMLConverter

Question

Я пытаюсь преобразовать файл PDF в формат HTML с помощью HTML Converter. Ниже приведен код, который я использую.

from django.conf import settings
settings.configure(PDF_MINER_IS_STRICT = True)
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import HTMLConverter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO
import re
import csv
def convert_pdf_to_html(path):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = HTMLConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    fp = file(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0 #is for all
    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().encode('utf-8')
    retstr.close()
    return str.encode('utf-8')

При запуске я получаю следующую ошибку:

Traceback (most recent call last):
  File "convertPDFToHTML.py", line 32, in <module>
    print convert_pdf_to_html(path)
  File "convertPDFToHTML.py", line 18, in convert_pdf_to_html
    device = HTMLConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
  File "C:\Python27\lib\site-packages\pdfminer\converter.py", line 247, in __init__
    PDFConverter.__init__(self, rsrcmgr, outfp, codec=codec, pageno=pageno, laparams=laparams)
  File "C:\Python27\lib\site-packages\pdfminer\converter.py", line 167, in __init__
    self.outfp.write(u"é")
UnicodeEncodeError: 'ascii' codec can't encode character u'\xe9' in position 0: ordinal not in range(128)

Я не уверен, как заставить 'converter.py' HTMLConverter следовать кодировке Unicode.

Пожалуйста помоги!

Answer 1

Мне удалось заставить это работать, интерпретируя выходную строку с кодировкой utf-8, используя .decode('utf-8') на месте .encode('utf-8')

from django.conf import settings
settings.configure(PDF_MINER_IS_STRICT = True)
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import HTMLConverter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO
import re
import csv
def convert_pdf_to_html(path):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = HTMLConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    fp = file(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0 #is for all
    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().decode('utf-8')
    retstr.close()
    return str # no need to encode