遇到不理解的 Unicode 错误

Question

这是我的代码，我知道看起来可能很糟糕，但它的功能都正常，唯一的问题就是最后一行...

import pyPdf
import os
import csv

class UnicodeWriter:
    """
    A CSV writer which will write rows to CSV file "f",
    which is encoded in the given encoding.
    """

    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
        # Redirect output to a queue
        self.queue = cStringIO.StringIO()
        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
        self.stream = f
        self.encoder = codecs.getincrementalencoder(encoding)()

    def writerow(self, row):
        self.writer.writerow([s.encode("utf-8") for s in row])
        # Fetch UTF-8 output from the queue ...
        data = self.queue.getvalue()
        data = data.decode("utf-8")
        # ... and reencode it into the target encoding
        data = self.encoder.encode(data)
        # write to the target stream
        self.stream.write(data)
        # empty queue
        self.queue.truncate(0)

    def writerows(self, rows):
        for row in rows:
            self.writerow(row)


    PDFWriter = csv.writer(open('/home/nick/TAM_work/text/text.doc', 'a'), delimiter=' ', quotechar='|', quoting=csv.QUOTE_ALL)

    def getPDFContent(path):
        content = ""
        # Load PDF into pyPDF
        pdf = pyPdf.PdfFileReader(file(path, "rb"))
        # Iterate pages
        for i in range(0, pdf.getNumPages()):
            # Extract text from page and add to content
            content += pdf.getPage(i).extractText() + "\n"
        # Collapse whitespace
        content = " ".join(content.replace(u"\xa0", " ").strip().split())
        return content

    for word in os.listdir("/home/nick/TAM_work/TAM_pdfs"):
     print getPDFContent("/home/nick/TAM_work/TAM_pdfs/" + word)

    PDFWriter.writerow ([getPDFContent("/home/nick/TAM_work/TAM_pdfs/" + word)])

当我运行它的时候，一切都正常，直到遇到这个...

Traceback (most recent call last):
  File "Saving_fuction_added.py", line 52, in <module>
    PDFWriter.writerow ([getPDFContent("/home/nick/TAM_work/TAM_pdfs/" + word)])
UnicodeEncodeError: 'ascii' codec can't encode character u'\u2122' in position 81: ordinal not in range(128)

我很希望能得到一些帮助。谢谢大家。

马特

Answer 1

根据我的理解，你把一个很大的数字放进了一个小的变量里，这就导致了一个错误。

我给你推荐一个在处理Unicode方面非常好用的C#工具，你可以在这里找到它：http://unicode.codeplex.com

在你的情况下，我建议你检查一下

 for i in range(0, pdf.getNumPages()): 

pdf.getNumPages()的值是否超过了128，确保它在这个范围内。

Answer 2

这是回答那个问题的代码。不过现在它只会写入最后一个文件。

  import pyPdf
import os
import csv

class UnicodeWriter:
    """
    A CSV writer which will write rows to CSV file "f",
    which is encoded in the given encoding.
    """

    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
        # Redirect output to a queue
        self.queue = cStringIO.StringIO()
        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
        self.stream = f
        self.encoder = codecs.getincrementalencoder(encoding)()

    def writerow(self, row):
        self.writer.writerow([s.encode("utf-8") for s in row])
        # Fetch UTF-8 output from the queue ...
        data = self.queue.getvalue()
        data = data.decode("utf-8")
        # ... and reencode it into the target encoding
        data = self.encoder.encode(data)
        # write to the target stream
        self.stream.write(data)
        # empty queue
        self.queue.truncate(0)

    def writerows(self, rows):
        for row in rows:
            self.writerow(row)


PDFWriter = csv.writer(open('/home/nick/TAM_work/text/text.doc', 'a'), delimiter=' ', quotechar='|', quoting=csv.QUOTE_ALL)

def getPDFContent(path):
    content = ""
    # Load PDF into pyPDF
    pdf = pyPdf.PdfFileReader(file(path, "rb"))
    # Iterate pages
    for i in range(0, pdf.getNumPages()):
        # Extract text from page and add to content
        content += pdf.getPage(i).extractText() + "\n"
    # Collapse whitespace
    content = " ".join(content.replace(u"\xa0", " ").strip().split())
    return content

for word in os.listdir("/home/nick/TAM_work/TAM_pdfs"):
    print getPDFContent("/home/nick/TAM_work/TAM_pdfs/" + word)

PDFWriter.writerow ([getPDFContent("/home/nick/TAM_work/TAM_pdfs/" + word).encode("ascii", "ignore")])