我正在寻找用Python将网页打印为本地文件PDF的解决方案。其中一个好的解决方案是使用Qt，在这里找到：https://bharatikunal.wordpress.com/2010/01/。
一开始它没有起作用，因为我在安装PyQt4时出了问题，它给出了错误消息，如 'ImportError: No module named PyQt4.QtCore' 和 'ImportError: No module named PyQt4.QtCore'。
这是因为PyQt4没有正确安装。我曾经把库位于C:\Python27\Lib，但这不适用于PyQt4。
事实上，只需要从http://www.riverbankcomputing.com/software/pyqt/download（注意您使用的正确Python版本），并将其安装到C:\Python27（我的情况）即可。
现在脚本运行得很好，所以我想分享它。有关使用Qprinter的更多选项，请参阅http://qt-project.org/doc/qt-4.8/qprinter.html#Orientation-enum。
您还可以使用pdfkit：
import pdfkit
pdfkit.from_url('http://google.com', 'out.pdf')
MacOS: brew install Caskroom/cask/wkhtmltopdf
Debian/Ubuntu: apt-get install wkhtmltopdf
Windows: choco install wkhtmltopdf
请参考官方文档以获取在MacOS/Ubuntu/其他操作系统上的安装指南：https://github.com/JazzCore/python-pdfkit/wiki/Installing-wkhtmltopdf
pip install weasyprint # No longer supports Python 2.x.
python
>>> import weasyprint
>>> pdf = weasyprint.HTML('http://www.google.com').write_pdf()
>>> len(pdf)
92059
>>> open('google.pdf', 'wb').write(pdf)
javascripts转换。为此，您需要使用pdfkit。 - suhailvsimport time
from pyPdf import PdfFileWriter, PdfFileReader
import StringIO
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
from xhtml2pdf import pisa
import sys
from PyQt4.QtCore import *
from PyQt4.QtGui import *
from PyQt4.QtWebKit import *
url = 'http://www.yahoo.com'
tem_pdf = "c:\\tem_pdf.pdf"
final_file = "c:\\younameit.pdf"
app = QApplication(sys.argv)
web = QWebView()
#Read the URL given
web.load(QUrl(url))
printer = QPrinter()
#setting format
printer.setPageSize(QPrinter.A4)
printer.setOrientation(QPrinter.Landscape)
printer.setOutputFormat(QPrinter.PdfFormat)
#export file as c:\tem_pdf.pdf
printer.setOutputFileName(tem_pdf)
def convertIt():
web.print_(printer)
QApplication.exit()
QObject.connect(web, SIGNAL("loadFinished(bool)"), convertIt)
app.exec_()
sys.exit
# Below is to add on the weblink as text and present date&time on PDF generated
outputPDF = PdfFileWriter()
packet = StringIO.StringIO()
# create a new PDF with Reportlab
can = canvas.Canvas(packet, pagesize=letter)
can.setFont("Helvetica", 9)
# Writting the new line
oknow = time.strftime("%a, %d %b %Y %H:%M")
can.drawString(5, 2, url)
can.drawString(605, 2, oknow)
can.save()
#move to the beginning of the StringIO buffer
packet.seek(0)
new_pdf = PdfFileReader(packet)
# read your existing PDF
existing_pdf = PdfFileReader(file(tem_pdf, "rb"))
pages = existing_pdf.getNumPages()
output = PdfFileWriter()
# add the "watermark" (which is the new pdf) on the existing page
for x in range(0,pages):
page = existing_pdf.getPage(x)
page.mergePage(new_pdf.getPage(0))
output.addPage(page)
# finally, write "output" to a real file
outputStream = file(final_file, "wb")
output.write(outputStream)
outputStream.close()
print final_file, 'is ready.'
html5lib存在一些问题，而xhtml2pdf使用了它。这个解决方案修复了这个问题：https://github.com/xhtml2pdf/xhtml2pdf/issues/318 - Blairg23.html文件，则需要使用该命令：pdfkit.from_file('test.html', 'out.pdf')
但是如果您没有将wkhtmltopdf可执行文件添加到系统路径中，这将会导致错误。这就是让我困惑的部分，我想分享一下。
在Windows上，打开您的环境变量并将它们添加到您的系统变量>路径中，如下所示。在我的情况下，安装了wkhtmltopdf之后，这些.exe文件位于以下位置：
C:\Program Files\wkhtmltopdf\bin
这里是一个正常工作的示例:
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_())
这里是使用QT的简单解决方案。我在StackOverFlow的另一个问题的答案中找到了它。我在Windows上测试过了。
from PyQt4.QtGui import QTextDocument, QPrinter, QApplication
import sys
app = QApplication(sys.argv)
doc = QTextDocument()
location = "c://apython//Jim//html//notes.html"
html = open(location).read()
doc.setHtml(html)
printer = QPrinter()
printer.setOutputFileName("foo.pdf")
printer.setOutputFormat(QPrinter.PdfFormat)
printer.setPageSize(QPrinter.A4);
printer.setPageMargins (15,15,15,15,QPrinter.Millimeter);
doc.print_(printer)
print "done!"
我尝试使用pdfkit来实现@NorthCat所提供的答案。
它需要先安装wkhtmltopdf。可以从这里下载安装程序。https://wkhtmltopdf.org/downloads.html
安装可执行文件后，可以写一行代码指示wkhtmltopdf的位置，像下面这样。（引用自Can't create pdf using python PDFKIT Error : " No wkhtmltopdf executable found:"
import pdfkit
path_wkthmltopdf = "C:\\Folder\\where\\wkhtmltopdf.exe"
config = pdfkit.configuration(wkhtmltopdf = path_wkthmltopdf)
pdfkit.from_url("http://google.com", "out.pdf", configuration=config)
我使用PyQt5版本5.15.0，这个解决方案对我有用。
import sys
from PyQt5 import QtWidgets, QtWebEngineWidgets
from PyQt5.QtCore import QUrl
from PyQt5.QtGui import QPageLayout, QPageSize
from PyQt5.QtWidgets import QApplication
if __name__ == '__main__':
app = QtWidgets.QApplication(sys.argv)
loader = QtWebEngineWidgets.QWebEngineView()
loader.setZoomFactor(1)
layout = QPageLayout()
layout.setPageSize(QPageSize(QPageSize.A4Extra))
layout.setOrientation(QPageLayout.Portrait)
loader.load(QUrl('https://dev59.com/-mAg5IYBdhLWcg3wo8P2))
loader.page().pdfPrintingFinished.connect(lambda *args: QApplication.exit())
def emit_pdf(finished):
loader.page().printToPdf("test.pdf", pageLayout=layout)
loader.loadFinished.connect(emit_pdf)
sys.exit(app.exec_())
pip install PyQtWebEngine 才能使其正常工作。 - Dániel Kis-Nagyimport sys
import json, base64
def send_devtools(driver, cmd, params={}):
resource = "/session/%s/chromium/send_command_and_get_result" % driver.session_id
url = driver.command_executor._url + resource
body = json.dumps({'cmd': cmd, 'params': params})
response = driver.command_executor._request('POST', url, body)
return response.get('value')
def get_pdf_from_html(driver, url, print_options={}, output_file_path="example.pdf"):
driver.get(url)
calculated_print_options = {
'landscape': False,
'displayHeaderFooter': False,
'printBackground': True,
'preferCSSPageSize': True,
}
calculated_print_options.update(print_options)
result = send_devtools(driver, "Page.printToPDF", calculated_print_options)
data = base64.b64decode(result['data'])
with open(output_file_path, "wb") as f:
f.write(data)
# example
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import shutil
# Check for the existence of the chromedriver executable
chromedriver = shutil.which("chromedriver")
assert chromedriver is not None, "chromedriver not on PATH"
url = "https://dev59.com/-mAg5IYBdhLWcg3wo8P2"
webdriver_options = Options()
webdriver_options.add_argument("--no-sandbox")
webdriver_options.add_argument('--headless')
webdriver_options.add_argument('--disable-gpu')
driver = webdriver.Chrome(chromedriver, options=webdriver_options)
get_pdf_from_html(driver, url)
driver.quit()
default_url_fetcher来处理cookies，但后来在Ubuntu16上安装时出现了问题。然后我使用了wkhtmltopdf，它支持cookie设置，但在处理某些页面时会引发许多OSERROR错误，例如-15 -11。 - Yuanmeng Xiaopdfkit.from_file('abc.html', 'abc.pdf')
pdfkit.from_file('abc.html', 'abc.pdf',options={"enable-local-file-access": ""})
OSError：wkhtmltopdf 报告了一个错误：由于网络错误 ProtocolUnknownError，退出代码为 1
Source: https://github.com/wkhtmltopdf/wkhtmltopdf/issues/2660#issuecomment-663063752