使用PyPDF2、reportlab和google翻译实现对英文pdf文档的自动翻译

前言

工作中遇到很多时候需要阅读英文PDF文档，英文读起来比较费劲，阅读效率也比较低，于是就想有没有办法自动把英文PDF自动翻译成中文呢？答案是肯定的，虽然有道词典这些工具可以自动取词翻译，但都是只能单个词的翻译，而现在google翻译已经做得非常好非常好准确了，可以整段整段的翻译，这对于辅助阅读，提高阅读效率是很有帮助的。

有了想法，马上就说干就干，思路就是读取PDF每页进行处理，调用google翻译的接口翻译成中文后后生成新的一页PDF，然后插入到原PDF页的后面，这样方便对照英文原文来看。

PDF读取和写入

PDF的读取和写入，可以使用PyPDF2方案，直接使用 pip 安装就可以了

pip install PyPDF2

PyPDF2 包含了 PdfFileReader PdfFileMerger PageObject PdfFileWriter 四个常用的主要 Class，其中PdfFileReader是用来读取pdf的，PdfFileWriter用来写pdf文件的，PageObject代表pdf每页的对象结构。

读取PDF文件的代码，这是获取所有页的文本：

from PyPDF2.pdf import PdfFileReader, PdfFileWriter, ContentStream

def getDataUsingPyPdf2(filename):
pdf = PdfFileReader(open(filename, "rb"))
content = ""
num = pdf.getNumPages()
for i in range(0, num):
extractedText = pdf.getPage(i).extractText()
content +=  extractedText + "\n"
return content

我们需要对每一页的文本进行翻译处理：

def dopage(page):
content = page["/Contents"].getObject()
if not isinstance(content, ContentStream):
content = ContentStream(content, pdf)

text = u_("")
for operands, operator in content.operations:
#print operator, operands
if operator == b_("Tj"):
_text = operands[0]
if isinstance(_text, TextStringObject):
text += _text + " "
elif operator == b_("rg"):
text += "\n"
elif operator == b_("T*"):
text += "\n"
elif operator == b_("'"):
text += "\n"
_text = operands[0]
if isinstance(_text, TextStringObject):
text += operands[0] + " "
elif operator == b_('"'):
_text = operands[2]
if isinstance(_text, TextStringObject):
text += _text + " "
elif operator == b_("TJ"):
for i in operands[0]:
if isinstance(i, TextStringObject):
text += i
text += " "

texts =
4000
text.split('. ')
results=''
for i in range(len(texts)):
try:
results = results + translate(str(texts[i])) + "\n"
except Exception as e:
print e
return results

这个函数其实是从extractText摘取出来的，只是为了更灵活的对文本进行处理而已，因为PDF的文本是割裂的，需要拼接起来，这个其实没完全处理好，只是做了简单的处理。

翻译方案

翻译采用的是google翻译，是从网上直接摘取的代码，做了少许修改优化，改成支持中文的，并且修改了翻译输出结果不完整的bug

#-*- coding:utf-8 -*

import re
import execjs
import urllib,urllib2
import sys
import json

reload(sys)
sys.setdefaultencoding( "utf-8" )

class Py4Js():
def __init__(self):
self.ctx = execjs.compile("""
function TL(a) {
var k = "";
var b = 406644;
var b1 = 3293161072;

var jd = ".";
var $b = "+-a^+6";
var Zb = "+-3^+b+-f";

for (var e = [], f = 0, g = 0; g < a.length; g++) {
var m = a.charCodeAt(g);
128 > m ? e[f++] = m : (2048 > m ? e[f++] = m >> 6 | 192 : (55296 == (m & 64512) && g + 1 < a.length && 56320 == (a.charCodeAt(g + 1) & 64512) ? (m = 65536 + ((m & 1023) << 10) + (a.charCodeAt(++g) & 1023),
e[f++] = m >> 18 | 240,
e[f++] = m >> 12 & 63 | 128) : e[f++] = m >> 12 | 224,
e[f++] = m >> 6 & 63 | 128),
e[f++] = m & 63 | 128)
}
a = b;
for (f = 0; f < e.length; f++) a += e[f],
a = RL(a, $b);
a = RL(a, Zb);
a ^= b1 || 0;
0 > a && (a = (a & 2147483647) + 2147483648);
a %= 1E6;
return a.toString() + jd + (a ^ b)
};

function RL(a, b) {
var t = "a";
var Yb = "+";
for (var c = 0; c < b.length - 2; c += 3) {
var d = b.charAt(c + 2),
d = d >= t ? d.charCodeAt(0) - 87 : Number(d),
d = b.charAt(c + 1) == Yb ? a >>> d: a << d;
a = b.charAt(c) == Yb ? a + d & 4294967295 : a ^ d
}
return a
}
""")

def getTk(self, text):
return self.ctx.call("TL", text)

def open_url(url):
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
req = urllib2.Request(url=url, headers=headers)
response = urllib2.urlopen(req)
data = response.read().decode('utf-8')
return data

def translate(content):
#print "content: ", content
js = Py4Js()
tk = js.getTk(content)

texts = ""
content = urllib2.quote(content)
url = "http://translate.google.cn/translate_a/single?client=t" \
"&sl=EN&tl=zh-CN&hl=zh-CNdt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca" \
"&dt=rw&dt=rm&dt=ss&dt=t&ie=UTF-8&oe=UTF-8&clearbtn=1&otf=1&pc=1" \
"&srcrom=0&ssel=0&tsel=0&kc=2&tk=%s&q=%s" % (tk, content)

result = open_url(url)
re = json.loads(result)
str = ""
for i in re[0]:
if i[0]:
str += i[0]
#print " ========>", i[0]
return str

if __name__ == "__main__":
text="您好"
texts=text.split('.')
results=''
for i in range(len(texts)):
try:
results = results + translate(str(texts[i]))
except Exception as e:
print e
print results

PDF页面生成

PDF页面生成采用的是reportlab方案，支持中文的话需要下载字体文件。PDF对换行处理也很麻烦，网上看了很多换行的方案，觉得都太复杂，还不如自己来实现换行，先用寻找换行符分割，然后每行42个字符，每drawString一行，坐标就就往下移即可，实现最简单的中文自动换行功能。

import StringIO
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont
pdfmetrics.registerFont(TTFont('msyh', 'Msyh.ttf'))

filename = "test.pdf"
pdf = PdfFileReader(open(filename, "rb"))
pdf_output = PdfFileWriter()
num = pdf.getNumPages()
for i in range(0, num):
print "do page: ", i
page = pdf.getPage(i)
pdf_output.addPage(page)
cnstr = dopage(page)

packet = StringIO.StringIO()
can = canvas.Canvas(packet, pagesize=letter)
can.setFont("msyh", 8)
can.setFontSize(12)
cnstrarr = cnstr.split("\n")
top = 750
for strline in cnstrarr:
for i in range(0, int(len(strline)/42)+1):
can.drawString(50, top, strline[i*42:i*42+42])
top -= 20
print "strline: ", strline
can.showPage()
can.save()
packet.seek(0)
new_pdf = PdfFileReader(packet)
pdf_output.addPage(new_pdf.getPage(0))

pdf_output.write(open("out.pdf", 'wb'))
print "Success!!"