优化文集PDF导出
This commit is contained in:
yangjian
parent
f509718d9d
commit
50bf6de540
@ -215,4 +215,14 @@ HAYSTACK_CONNECTIONS = {
|
||||
# 当添加、修改、删除数据时，自动生成索引
|
||||
HAYSTACK_SIGNAL_PROCESSOR = 'haystack.signals.RealtimeSignalProcessor'
|
||||
# 自定义高亮
|
||||
HAYSTACK_CUSTOM_HIGHLIGHTER = "app_doc.search.highlight.MyHighLighter"
|
||||
HAYSTACK_CUSTOM_HIGHLIGHTER = "app_doc.search.highlight.MyHighLighter"
|
||||
|
||||
# Selenium 调用的driver类型 默认为Chromium
|
||||
try:
|
||||
CHROMIUM_DRIVER = CONFIG['selenium']['driver']
|
||||
except:
|
||||
CHROMIUM_DRIVER = 'CHROMIUM'
|
||||
if 'driver_path' in CONFIG['selenium'].keys():
|
||||
CHROMIUM_DRIVER_PATH = CONFIG['selenium']['driver_path']
|
||||
else:
|
||||
CHROMIUM_DRIVER_PATH = None
|
||||
|
||||
@ -4,42 +4,94 @@
|
||||
# #日期：2020/12/27
|
||||
# 博客地址：zmister.com
|
||||
|
||||
from selenium import webdriver
|
||||
from selenium.webdriver.chrome.options import Options
|
||||
from selenium.common.exceptions import TimeoutException
|
||||
from selenium.webdriver.support.ui import WebDriverWait
|
||||
from selenium.webdriver.support.expected_conditions import staleness_of
|
||||
from webdriver_manager.chrome import ChromeDriverManager
|
||||
from webdriver_manager.utils import ChromeType
|
||||
from django.conf import settings
|
||||
import sys
|
||||
from urllib.parse import quote
|
||||
from PyQt5 import QtCore, QtWidgets, QtWebEngineWidgets, QtGui
|
||||
# print(sys.path)
|
||||
import json
|
||||
import base64
|
||||
|
||||
|
||||
def html2pdf(html_path,pdf_path):
|
||||
html_path = '/'.join(html_path.split('\\'))
|
||||
html_path = quote(html_path, safe='/:?=')
|
||||
# 实例化一个Qt应用
|
||||
app = QtWidgets.QApplication(sys.argv)
|
||||
# 实例化一个WebEngineView
|
||||
loader = QtWebEngineWidgets.QWebEngineView()
|
||||
# 设置视图缩放比例
|
||||
loader.setZoomFactor(1)
|
||||
# 设置页码打印完成后的槽
|
||||
loader.page().pdfPrintingFinished.connect(loader.close)
|
||||
# 请求HTML文件
|
||||
loader.load(QtCore.QUrl("file:///{}".format(html_path)))
|
||||
def convert(source: str, target: str, timeout: int = 2, compress: bool = False, power: int = 0, install_driver: bool = True):
|
||||
'''
|
||||
Convert a given html file or website into PDF
|
||||
|
||||
def emit_pdf(finished):
|
||||
layout = QtGui.QPageLayout()
|
||||
layout.setPageSize(QtGui.QPageSize(QtGui.QPageSize.A4Extra))
|
||||
layout.setLeftMargin(20)
|
||||
layout.setRightMargin(20)
|
||||
layout.setTopMargin(20)
|
||||
layout.setBottomMargin(20)
|
||||
layout.setOrientation(QtGui.QPageLayout.Portrait)
|
||||
loader.page().printToPdf(pdf_path, pageLayout=layout)
|
||||
:param str source: source html file or website link
|
||||
:param str target: target location to save the PDF
|
||||
:param int timeout: timeout in seconds. Default value is set to 2 seconds
|
||||
:param bool compress: whether PDF is compressed or not. Default value is False
|
||||
:param int power: power of the compression. Default value is 0. This can be 0: default, 1: prepress, 2: printer, 3: ebook, 4: screen
|
||||
'''
|
||||
|
||||
# 加载完成后连接到PDF打印方法
|
||||
loader.loadFinished.connect(emit_pdf)
|
||||
app.exec_()
|
||||
result = __get_pdf_from_html(source, timeout, install_driver)
|
||||
|
||||
# if compress:
|
||||
# __compress(result, target, power)
|
||||
# else:
|
||||
with open(target, 'wb') as file:
|
||||
file.write(result)
|
||||
|
||||
|
||||
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)
|
||||
|
||||
if not response:
|
||||
raise Exception(response.get('value'))
|
||||
|
||||
return response.get('value')
|
||||
|
||||
|
||||
def __get_pdf_from_html(path: str, timeout: int, install_driver: bool, print_options={}):
|
||||
webdriver_options = Options()
|
||||
webdriver_prefs = {}
|
||||
driver = None
|
||||
|
||||
webdriver_options.add_argument('--headless')
|
||||
webdriver_options.add_argument('--disable-gpu')
|
||||
webdriver_options.add_argument('--no-sandbox')
|
||||
webdriver_options.add_argument('--disable-dev-shm-usage')
|
||||
webdriver_options.experimental_options['prefs'] = webdriver_prefs
|
||||
|
||||
webdriver_prefs['profile.default_content_settings'] = {'images': 2}
|
||||
|
||||
if install_driver:
|
||||
driver = webdriver.Chrome(
|
||||
ChromeDriverManager(
|
||||
url='https://npm.taobao.org/mirrors/chromedriver/',
|
||||
latest_release_url='https://npm.taobao.org/mirrors/chromedriver/LATEST_RELEASE',
|
||||
chrome_type=ChromeType.GOOGLE if settings.CHROMIUM_DRIVER == 'Chrome' else ChromeType.CHROMIUM
|
||||
).install(),
|
||||
options=webdriver_options
|
||||
)
|
||||
else:
|
||||
driver = webdriver.Chrome(options=webdriver_options)
|
||||
|
||||
driver.get(path)
|
||||
|
||||
try:
|
||||
WebDriverWait(driver, timeout).until(staleness_of(driver.find_element_by_tag_name('html')))
|
||||
except TimeoutException:
|
||||
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)
|
||||
driver.quit()
|
||||
return base64.b64decode(result['data'])
|
||||
|
||||
if __name__ == '__main__':
|
||||
# print(sys.argv)
|
||||
html_path, pdf_path = sys.argv[1],sys.argv[2]
|
||||
html2pdf(html_path=html_path,pdf_path=pdf_path)
|
||||
convert(html_path,pdf_path)
|
||||
# html2pdf(html_path=html_path,pdf_path=pdf_path)
|
||||
|
||||
@ -21,6 +21,7 @@ django.setup()
|
||||
from app_doc.models import *
|
||||
from subprocess import Popen
|
||||
from loguru import logger
|
||||
from app_doc.report_html2pdf import convert
|
||||
import traceback
|
||||
import time
|
||||
import json
|
||||
@ -705,7 +706,7 @@ class ReportPDF():
|
||||
try:
|
||||
project = Project.objects.get(pk=self.pro_id)
|
||||
except:
|
||||
return
|
||||
return False
|
||||
# 拼接文档的HTML字符串
|
||||
data = Doc.objects.filter(top_doc=self.pro_id,parent_doc=0).order_by("sort")
|
||||
toc_list = {'1':[],'2':[],'3':[]}
|
||||
@ -755,10 +756,6 @@ class ReportPDF():
|
||||
temp_file_path = report_pdf_folder + '/{0}.html'.format(temp_file_name)
|
||||
# PDF文件路径
|
||||
report_file_path = report_pdf_folder + '/{0}.pdf'.format(temp_file_name)
|
||||
# output_pdf_path = report_pdf_folder + '/{}_{}.pdf'.format(
|
||||
# project.name,
|
||||
# str(datetime.datetime.today()).replace(' ','-').replace(':','-')
|
||||
# )
|
||||
# 写入HTML文件
|
||||
with open(temp_file_path, 'w', encoding='utf-8') as htmlfile:
|
||||
htmlfile.write(
|
||||
@ -772,16 +769,14 @@ class ReportPDF():
|
||||
)
|
||||
|
||||
# 执行HTML转PDF
|
||||
# html_to_pdf(temp_file_path,report_file_path)
|
||||
# print(os.getcwd())
|
||||
shell_path = os.path.join(os.getcwd(),'app_doc/report_html2pdf.py')
|
||||
html2pdf = Popen(['python',shell_path,temp_file_path,report_file_path])
|
||||
html2pdf.wait()
|
||||
for proc in psutil.process_iter():
|
||||
if proc.name().startswith('QtWebEngineProcess'):
|
||||
proc.kill()
|
||||
try:
|
||||
convert(temp_file_path,report_file_path)
|
||||
except:
|
||||
logger.error("生成PDF出错")
|
||||
return False
|
||||
# 处理PDF文件
|
||||
if os.path.exists(report_file_path):
|
||||
os.remove(temp_file_path)
|
||||
return report_file_path
|
||||
else:
|
||||
return False
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
[site]
|
||||
# True表示开启站点调试模式，False表示关闭站点调试模式
|
||||
debug = False
|
||||
debug = True
|
||||
|
||||
[database]
|
||||
# engine，指定数据库类型，接受sqlite、mysql、oracle、postgresql
|
||||
@ -14,4 +14,6 @@ engine = sqlite
|
||||
# host表示数据库主机地址
|
||||
# host = db_host
|
||||
# port表示数据库端口
|
||||
# port = db_port
|
||||
# port = db_port
|
||||
[selenium]
|
||||
# driver = Chrome
|
||||
@ -13,6 +13,6 @@ Markdown==3.3.3
|
||||
jieba==0.42.1
|
||||
mammoth==1.4.13
|
||||
markdownify==0.6.0
|
||||
psutil==5.8.0
|
||||
PyQt5==5.11.3
|
||||
selenium==3.141.0
|
||||
webdriver_manager==3.3.0
|
||||
PyYAML==5.4.1
|
||||
Loading…
x
Reference in New Issue
Block a user