CssParser错误，转换HTML为PDF时，PISA与Python

Question

我正在尝试使用pisa和python把html文档转换成pdf文件。对于小的html代码，这个方法运行得很好。但是当我尝试处理像google.com的html数据，或者任何大的html文件时，就会出现错误。

下面是用来将html转换成pdf的代码：

import ho.pisa as pisa
import sys
import os
ls =[]
for arg in sys.argv:
    ls.append(arg)
pisa.showLogging()
print ls

html_file = open(ls[1])
HTML = html_file.read()
filename = os.path.basename(str(ls[1]))
print filename
str(os.getcwd()+filename)
pdfFile =open(str(os.getcwd()+filename), "wb")
pdf = pisa.CreatePDF(HTML,pdfFile)

if not pdf.err:
    print "ds"
    pisa.startViewer(filename)

pdfFile.close()
html_file.close()

这是出现的错误信息：

ERROR [ho.pisa] C:\Python27\lib\site-packages\sx\pisa3\pisa_document.py line 223: Document error

Traceback (most recent call last):
  File "C:\Python27\lib\site-packages\sx\pisa3\pisa_document.py", line 128, in pisaDocument
    c = pisaStory(src, path, link_callback, debug, default_css, xhtml, encoding,
 c=c, xml_output=xml_output)
  File "C:\Python27\lib\site-packages\sx\pisa3\pisa_document.py", line 73, in pisaStory
    pisaParser(src, c, default_css, xhtml, encoding, xml_output)
  File "C:\Python27\lib\site-packages\sx\pisa3\pisa_parser.py", line 626, in pisaParser
    c.parseCSS()
  File "C:\Python27\lib\site-packages\sx\pisa3\pisa_context.py", line 545, in parseCSS
    self.css = self.cssParser.parse(self.cssText)
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 358, in parse
    src, stylesheet = self._parseStylesheet(src)
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 453, in _parseStylesheet
    src, atResults = self._parseAtKeyword(src)
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 577, in _parseAtKeyword
    src, result = self._parseAtIdent(src)
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 722, in _parseAtIdent
    src, stylesheet = self._parseStylesheet(src)
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 458, in _parseStylesheet
    src, ruleset = self._parseRuleset(src)
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 737, in _parseRuleset
    src, properties = self._parseDeclarationGroup(src.lstrip())
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 922, in _parseDeclarationGroup
    raise self.ParseError('Declaration group closing \'}\' not found', src, ctxsrc)
CSSParseError: Declaration group closing '}' not found:: (u'{', u'0%{opacity:0}50%{opa')
Traceback (most recent call last):
  File "trypdf.py", line 16, in <module>
    pdf = pisa.CreatePDF(HTML,pdfFile)
  File "C:\Python27\lib\site-packages\sx\pisa3\pisa_document.py", line 128, in pisaDocument
    c = pisaStory(src, path, link_callback, debug, default_css, xhtml, encoding,
 c=c, xml_output=xml_output)
  File "C:\Python27\lib\site-packages\sx\pisa3\pisa_document.py", line 73, in pisaStory
pisaParser(src, c, default_css, xhtml, encoding, xml_output)
  File "C:\Python27\lib\site-packages\sx\pisa3\pisa_parser.py", line 626, in pisaParser
    c.parseCSS()
  File "C:\Python27\lib\site-packages\sx\pisa3\pisa_context.py", line 545, in parseCSS
self.css = self.cssParser.parse(self.cssText)
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 358, in parse
src, stylesheet = self._parseStylesheet(src)
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 453, in _parseStylesheet
    src, atResults = self._parseAtKeyword(src)
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 577, in _parseAtKeyword
    src, result = self._parseAtIdent(src)
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 722, in _parseAtIdent
    src, stylesheet = self._parseStylesheet(src)
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 458, in _parseStylesheet
    src, ruleset = self._parseRuleset(src)
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 737, in _parseRuleset
    src, properties = self._parseDeclarationGroup(src.lstrip())
  File "C:\Python27\lib\site-packages\sx\w3c\cssParser.py", line 922, in _parseDeclarationGroup
    raise self.ParseError('Declaration group closing \'}\' not found', src, ctxsrc)
sx.w3c.cssParser.CSSParseError: Declaration group closing '}' not found:: (u'{', u'0%{opacity:0}50%{opa')

Answer 1

xhmlt2pdf 这个工具并不是适合所有网站。如果你想转换网页为PDF，可以试试 pdfkit：

import pdfkit
pdfkit.from_url('http://google.com', 'out.pdf')

补充： 我找到了一种用 PyQt 的新方法（来自 这里, 感谢 Mark K）：

import sys 
from PyQt4.QtCore import *
from PyQt4.QtGui import * 
from PyQt4.QtWebKit import * 

app = QApplication(sys.argv)
web = QWebView()
web.load(QUrl("http://www.yahoo.com"))
printer = QPrinter()
printer.setPageSize(QPrinter.A4)
printer.setOutputFormat(QPrinter.PdfFormat)
printer.setOutputFileName("fileOK.pdf")

def convertIt():
    web.print_(printer)
    print "Pdf generated"
    QApplication.exit()

QObject.connect(web, SIGNAL("loadFinished(bool)"), convertIt)
sys.exit(app.exec_())