Question

我正在尝试使用iTextSharp（v5.5.12.1）从以下PDF中提取文本： https://structure.mil.ru/files/morf/military/files/ENGV_1929.pdf

不幸的是，似乎他们使用了许多嵌入式自定义字体，这使我不胜其烦。

就目前而言，我有一个使用OCR的可行解决方案，但是OCR可能不精确，错误地读取了一些字符，并且在字符之间添加了额外的空格。如果我可以直接提取文本，那将是理想的选择。

    ```
public static string ExtractTextFromPdf(Stream pdfStream, bool addNewLineBetweenPages = false)
        {
            using (PdfReader reader = new PdfReader(pdfStream))
            {
                string text = "";

                for (int i = 1; i <= reader.NumberOfPages; i++)
                {
                    text += PdfTextExtractor.GetTextFromPage(reader, i);
                    if (addNewLineBetweenPages && i != reader.NumberOfPages)
                    {
                        text += Environment.NewLine;
                    }
                }

                return text;
            }
        }

Answer 1

这里的问题是嵌入式字体程序中的字形具有非标准字形名称（ G00 ， G01 ，...），并且只能由字形标识名称。因此，必须建立从这些字形名称到Unicode字符的映射。一个人可以这样做通过检查PDF中的字体程序（例如使用字体伪造）并通过名称直观地识别字形。例如。就像这里

（如您所知，有问题的字体的字形存在一些空白，这些字形在手头的文档中并未使用。您可能会猜到一些缺失的字形，而有些则没有。）

然后，您必须将这些映射注入到iText中。由于映射是隐藏的（private static类的GlyphList成员），因此您必须修补iText本身或使用反射：

void InitializeGlyphs()
{
    FieldInfo names2unicodeFiled = typeof(GlyphList).GetField("names2unicode", BindingFlags.Instance | BindingFlags.NonPublic | BindingFlags.Static);
    Dictionary<string, int[]> names2unicode = (Dictionary<string, int[]>) names2unicodeFiled.GetValue(null);
    names2unicode["G03"] = new int[] { ' ' };

    names2unicode["G0A"] = new int[] { '\'' };
    names2unicode["G0B"] = new int[] { '(' };
    names2unicode["G0C"] = new int[] { ')' };

    names2unicode["G0F"] = new int[] { ',' };
    names2unicode["G10"] = new int[] { '-' };
    names2unicode["G11"] = new int[] { '.' };
    names2unicode["G12"] = new int[] { '/' };
    names2unicode["G13"] = new int[] { '0' };
    names2unicode["G14"] = new int[] { '1' };
    names2unicode["G15"] = new int[] { '2' };
    names2unicode["G16"] = new int[] { '3' };
    names2unicode["G17"] = new int[] { '4' };
    names2unicode["G18"] = new int[] { '5' };
    names2unicode["G19"] = new int[] { '6' };
    names2unicode["G1A"] = new int[] { '7' };
    names2unicode["G1B"] = new int[] { '8' };
    names2unicode["G1C"] = new int[] { '9' };
    names2unicode["G1D"] = new int[] { ':' };

    names2unicode["G23"] = new int[] { '@' };
    names2unicode["G24"] = new int[] { 'A' };
    names2unicode["G25"] = new int[] { 'B' };
    names2unicode["G26"] = new int[] { 'C' };
    names2unicode["G27"] = new int[] { 'D' };
    names2unicode["G28"] = new int[] { 'E' };
    names2unicode["G29"] = new int[] { 'F' };
    names2unicode["G2A"] = new int[] { 'G' };
    names2unicode["G2B"] = new int[] { 'H' };
    names2unicode["G2C"] = new int[] { 'I' };
    names2unicode["G2D"] = new int[] { 'J' };
    names2unicode["G2E"] = new int[] { 'K' };
    names2unicode["G2F"] = new int[] { 'L' };
    names2unicode["G30"] = new int[] { 'M' };
    names2unicode["G31"] = new int[] { 'N' };
    names2unicode["G32"] = new int[] { 'O' };
    names2unicode["G33"] = new int[] { 'P' };
    names2unicode["G34"] = new int[] { 'Q' };
    names2unicode["G35"] = new int[] { 'R' };
    names2unicode["G36"] = new int[] { 'S' };
    names2unicode["G37"] = new int[] { 'T' };
    names2unicode["G38"] = new int[] { 'U' };
    names2unicode["G39"] = new int[] { 'V' };
    names2unicode["G3A"] = new int[] { 'W' };
    names2unicode["G3B"] = new int[] { 'X' };
    names2unicode["G3C"] = new int[] { 'Y' };
    names2unicode["G3D"] = new int[] { 'Z' };

    names2unicode["G42"] = new int[] { '_' };

    names2unicode["G44"] = new int[] { 'a' };
    names2unicode["G45"] = new int[] { 'b' };
    names2unicode["G46"] = new int[] { 'c' };
    names2unicode["G46._"] = new int[] { 'c' };
    names2unicode["G47"] = new int[] { 'd' };
    names2unicode["G48"] = new int[] { 'e' };
    names2unicode["G49"] = new int[] { 'f' };
    names2unicode["G4A"] = new int[] { 'g' };
    names2unicode["G4B"] = new int[] { 'h' };
    names2unicode["G4C"] = new int[] { 'i' };
    names2unicode["G4D"] = new int[] { 'j' };
    names2unicode["G4E"] = new int[] { 'k' };
    names2unicode["G4F"] = new int[] { 'l' };
    names2unicode["G50"] = new int[] { 'm' };
    names2unicode["G51"] = new int[] { 'n' };
    names2unicode["G52"] = new int[] { 'o' };
    names2unicode["G53"] = new int[] { 'p' };
    names2unicode["G54"] = new int[] { 'q' };
    names2unicode["G55"] = new int[] { 'r' };
    names2unicode["G56"] = new int[] { 's' };
    names2unicode["G57"] = new int[] { 't' };
    names2unicode["G58"] = new int[] { 'u' };
    names2unicode["G59"] = new int[] { 'v' };
    names2unicode["G5A"] = new int[] { 'w' };
    names2unicode["G5B"] = new int[] { 'x' };
    names2unicode["G5C"] = new int[] { 'y' };
    names2unicode["G5D"] = new int[] { 'z' };

    names2unicode["G62"] = new int[] { 'Ш' };
    names2unicode["G63"] = new int[] { 'Р' };
    names2unicode["G6A"] = new int[] { 'И' };
    names2unicode["G6B"] = new int[] { 'А' };
    names2unicode["G6C"] = new int[] { 'М' };
    names2unicode["G6D"] = new int[] { 'в' };
    names2unicode["G6E"] = new int[] { 'Ф' };
    names2unicode["G70"] = new int[] { 'Е' };
    names2unicode["G72"] = new int[] { 'Б' };
    names2unicode["G73"] = new int[] { 'Н' };
    names2unicode["G76"] = new int[] { 'С' };
    names2unicode["G7A"] = new int[] { 'К' };
    names2unicode["G7B"] = new int[] { 'В' };
    names2unicode["G7C"] = new int[] { 'О' };
    names2unicode["G7D"] = new int[] { 'к' };
    names2unicode["G7E"] = new int[] { 'З' };
    names2unicode["G80"] = new int[] { 'Г' };
    names2unicode["G81"] = new int[] { 'П' };
    names2unicode["G82"] = new int[] { 'у' };
    names2unicode["G85"] = new int[] { '»' };
    names2unicode["G88"] = new int[] { 'т' };
    names2unicode["G8D"] = new int[] { '’' };
    names2unicode["G90"] = new int[] { 'У' };
    names2unicode["G91"] = new int[] { 'Т' };
    names2unicode["GA1"] = new int[] { 'Ц' };
    names2unicode["GA2"] = new int[] { '№' };
    names2unicode["GAA"] = new int[] { 'э' };
    names2unicode["GAB"] = new int[] { 'я' };
    names2unicode["GAC"] = new int[] { 'і' };
    names2unicode["GAD"] = new int[] { 'б' };
    names2unicode["GAE"] = new int[] { 'й' };
    names2unicode["GAF"] = new int[] { 'р' };
    names2unicode["GB0"] = new int[] { 'с' };
    names2unicode["GB2"] = new int[] { 'х' };
    names2unicode["GB5"] = new int[] { '“' };
    names2unicode["GB9"] = new int[] { 'п' };
    names2unicode["GBA"] = new int[] { 'о' };
    names2unicode["GBD"] = new int[] { '«' };
    names2unicode["GC1"] = new int[] { 'ф' };
    names2unicode["GC8"] = new int[] { 'а' };
    names2unicode["GCB"] = new int[] { 'е' };
    names2unicode["GCE"] = new int[] { 'ж' };
    names2unicode["GCF"] = new int[] { 'з' };
    names2unicode["GD2"] = new int[] { 'и' };
    names2unicode["GD3"] = new int[] { 'н' };
    names2unicode["GDC"] = new int[] { '–' };
    names2unicode["GE3"] = new int[] { 'л' };
}

执行该方法后，您可以使用方法提取文本：

InitializeGlyphs();

using (FileStream pdfStream = new FileStream(@"ENGV_1929.pdf", FileMode.Open))
{
    string result = ExtractTextFromPdf(pdfStream, true);
    File.WriteAllText(@"ENGV_1929.txt", result);
    Console.WriteLine("\n\nENGV_1929.pdf\n");
    Console.WriteLine(result);
}

结果：

From Notices to Mariners
Edition No 29/2019
(English version)
Notiсes to Mariners from Seсtion II «Сharts Сorreсtion», based on the original sourсe information, and
NAVAREA XIII, XX and XXI navigational warnings are reprinted hereunder in English. Original Notiсes to
Mariners from Seсtion I «Misсellaneous Navigational Information» and from Seсtion III «Nautiсal
Publiсations Сorreсtion» may be only briefly annotated and/or a referenсe may be made to Notiсes from
other Seсtions. Information from Seсtion IV «Сatalogues of Сharts and Nautiсal Publiсations Сorreсtion»
сonсerning the issue of сharts and publiсations is presented with details.
Digital analogue of English version of the extracts from original Russian Notices to Mariners is available
by: http://structure.mil.ru/structure/forces/hydrographic/info/notices.htm
СНАRTS СОRRЕСTIОN
Вarents Sea
 3493 Сharts 18012, 17052, 15005, 15004
Amend 1. Light to light Fl G 4s 1M at
 front leading lightbeacon 69111’32.2“N 33129’48.0“E
 2. Light to light Fl G 4s 1M at
 rear leading lightbeacon 69111’34.85“N 33129’44.25“E
 Cancel coastal warning
 MURMANSK 71/19
...

当心，您会发现经常使用相似外观的西里尔字母代替拉丁字符。显然，文档是由不认为印刷正确性非常重要的人手动创建的。

因此，如果您要在文本中进行搜索，则应首先对文本和搜索词进行规范化（例如，对拉丁字母'c'和西里尔字母'с'使用相同的字符）。

使用带有嵌入字体的iText提取文本

1 个答案: