在PDF文件中使用Python搜索

Question

这里是PDF结构的一部分：

5 0 obj
<< /Length 56 >>
stream
BT /F1 12 Tf 100 700 Td 15 TL (JavaScript example) Tj ET
endstream
endobj
6 0 obj
<<
/Type /Font
/Subtype /Type1
/Name /F1
/BaseFont /Helvetica
/Encoding /MacRomanEncoding
>>
endobj
7 0 obj
<<
/Type /Action
/S /JavaScript

我想查找“javascript”这个词，不管它是否存在。问题在于，“javascript”可以用十六进制表示，可能是完整的，也可能是部分的，比如“javascript”或者“Jav#61Script”或者“J#61v#61Script”等等。

那么，我该怎么才能找到“javascript”这个词，考虑到所有这些可能性呢？？？

Answer 1

逐个读取字符，并在这个过程中把你发现的十六进制数转换成字符，同时把它们转换成小写字母。然后把结果和“javascript”进行比较。

这里有个想法：

import string
import os
import re

def pdf_find_str(pdfname, str):
  f = open(pdfname, "rb")

  # read the file CHUNK_SIZE chars at a time, keeping last KEEP_SIZE chars
  CHUNK_SIZE = 2*1024*1024
  KEEP_SIZE = 3 * len(str) # each char might be in #ff form
  hexvals = "0123456789abcdef"

  ichunk = removed = 0
  chunk = f.read(CHUNK_SIZE)
  while len(chunk) > 0:

    # Loop to find all #'s and replace them with the character they represent.
    hpos = chunk.find('#')
    while hpos != -1:
      if len(chunk)-hpos >= 3 and chunk[hpos+1] in hexvals and chunk[hpos+2] in hexvals:
        hex = int(chunk[hpos+1:hpos+3], 16)  # next two characters are int value
        ch = chr(hex).lower()
        if ch in str: # avoid doing this if ch is not in str
          chunk = chunk[:hpos] + ch + chunk[hpos+3:]
          removed += 2
      hpos = chunk.find('#', hpos+1)

    m = re.search(str, chunk, re.I)
    if m:
      return ichunk * (CHUNK_SIZE-KEEP_SIZE) + m.start()

    # Transfer last KEEP_SIZE characters to beginning for next round of
    # testing since our string may span chunks.
    next_chunk = f.read(CHUNK_SIZE - KEEP_SIZE)
    if len(next_chunk) == 0: break
    chunk = chunk[-KEEP_SIZE:] + next_chunk

    ichunk += 1

  f.close()
  return -1

# On one file:
#if pdf_find_str("Consciousness Explained.pdf", "javascript") != -1:
#  print 'Contains "javascript"'

# Recursively on a directory:
for root, dirs, files in os.walk("Books"):
  for file in files:
    if file.endswith(".pdf"):
      position = pdf_find_str(root + "/" + file, "javascript")
      if position != -1:
        print file, "(", position, ")"
# Note: position returned by pdf_find_str does not account for removed
# characters from #ff representations (if any).