【实战】Python将微信文章保存为PDF

微信文章链接：https://mp.weixin.qq.com/s/imfnV7q8WY8gwDLYBir_pw

'''将网页url生成pdf文件'''

headers = [
    ('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'),
    ]

options = {
     'custom-header': headers,
    'debug-javascript': [''],
    'javascript-delay': 10000,
    'no-stop-slow-scripts': "",
    'load-media-error-handling': 'abort',
 } 

def url_to_pdf(url, fpath):
    # 将wkhtmltopdf.exe程序绝对路径传入config对象（如果刚安装wkhtmltopdf未重启电脑）
    path_wkthmltopdf = r'E:\Software\wkhtmltopdf\bin\wkhtmltopdf.exe'
    config = pdfkit.configuration(wkhtmltopdf=path_wkthmltopdf)
    # 生成pdf文件，fpath为文件路径
    pdfkit.from_url(url, fpath, configuration=config, options=options)
    print('完成：', fpath)

url_to_pdf(url, 'out_file.pdf')

生成PDF文件：

原因：html代码中图片链接属性是 data-src，未识别出图片链接

此外，还有图片url要用绝对路径

 

使用requests库获取html源码，将 data-src替换为src

import pdfkit
import requests
from bs4 import BeautifulSoup

res = requests.get(url)
# data-src替换为src 有时候返回的正文被隐藏了，将hidden去掉
html = res.text.replace("data-src", "src").replace('style="visibility: hidden;"',"")

soup = BeautifulSoup(html)
# 选择正文（去除javascrapt等）
html = soup.select('div#img-content')[0]

# 可以修改字体
font = '''
<style type="text/css">
     @font-face{font-family: "微软雅黑";src:url("‪C:\\Windows\\Fonts\\msyh.ttc")
</style>
 <style type = "text/css">
    p { font-family: '微软雅黑', cursive; }
</style>
'''
html = font + str(html)

# 选项
options = {
    'page-size': 'A4',
#     'margin-top': '0.75in',
#     'margin-right': '0.75in',
#     'margin-bottom': '0.75in',
#     'margin-left': '0.75in',
    'encoding': "UTF-8",
#      'custom-header': headers,
#     'debug-javascript': [''],
#     'javascript-delay': 10000,
#     'no-stop-slow-scripts': "",
#     'load-media-error-handling': 'abort',
 } 

path_wkthmltopdf = r'E:\Software\wkhtmltopdf\bin\wkhtmltopdf.exe'
config = pdfkit.configuration(wkhtmltopdf=path_wkthmltopdf)

pdfkit.from_string(str(html), 'outfile5.pdf', configuration=config, options=options)

 最终得到和网页一样的PDF