我想将pdf转换为文本。我在 python 命令提示符下尝试了这段代码,但没有显示任何输出。也许我错了。你能告诉我我哪里错了吗?提前致谢。
import pyPdf
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
print getPDFContent("test.pdf").encode("ascii", "ignore")