保存vx文章到pdf文件

helian147

目的：
保存一些零散公众号文章到pdf，不是采集某个公众号全部文章【可以用夜泉大神的WeChatDownload，论坛有下载】。
这程序没啥用，会的无须用嘛

实现：
1、复制公众号链接【试了几次发现拷贝到QQ，登陆PC QQ再复制全部链接比较方便】链接全部复制到指定txt文件，txt文件内容无需排版、会自动提取链接；
2、运行程序，pdf保存在指定目录。

需要修改：
1、txt文件的目录，由path参数指定，默认桌面
2、pdf保存在指定目录path下的pdf目录，不存在会新建pdf目录，也可自己修改
3、options选项：page-size指定页面大小；zoom指定缩放【有时文章带CODE太长而打印PDF不全，可以缩放试试】，pdf打印出来效果可以调整试试。

感谢论坛大神【收藏夹太多没找到】，代码大部分是参考的【拷贝的】

[Python] 纯文本查看 复制代码

import pdfkit
import requests
from bs4 import BeautifulSoup
import os
import re
import time

urls = []

def txt_get_url(txt_file):
    f = open(txt_file, 'r')
    f_content = f.readlines()
    f.close()
    return f_content



def url_pdf(url):
    headers = {
    #'content-type':'application/json',
    #'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
    'accept-encoding': 'gzip, deflate, br',
    'accept-language': 'zh-CN,zh;q=0.9',
    #'sec-fetch-dest': 'document',
    #'sec-fetch-mode': 'navigate',
    #'sec-fetch-site': 'none',
    #'upgrade-insecure-requests': 1,
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36'
        }

    res = requests.get(url, headers=headers)

    # 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, "lxml")

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

    title = soup.find('h2').string.replace('\n','').replace(' ', '').replace('\u200b', '').replace('\ufeff', '').replace('\ue601','')
    rstr = r"[\/\\\:\*\?\"\<\>\|]"          ## cannot save file
    new_title = re.sub(rstr, '_', title)

    author_name = soup.find('a', id='js_name').string.replace('\n','').replace(' ', '').replace('\u200b', '').replace('\ufeff', '').replace('\ue601','')
    author_name = re.sub(rstr, '_', author_name)

    title_name = author_name + '-' + new_title + '.pdf'
    #title_file_name = "".join(re.findall(r'[\u4e00-\u9fa5]+', title_name))


    # 可以修改字体
    font = '''
    <style type="text/css">
        @font-face{font-family: "微软雅黑";src:url("&#8234;C:\\Windows\\Fonts\\msyh.ttc")
    </style>
    <style type = "text/css">
        p { font-family: '微软雅黑', cursive; }
    </style>
    '''
    html = font + str(html)

    #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'),]

    # 选项
    options = {
        'page-size': 'A4',
    #    'margin-top': '0',
        'margin-right': '3mm',
    #    'margin-bottom': '0',
        'margin-left': '3mm',
    #    'disable-smart-shrinking': [''],
        'zoom': '0.9',                    # too long code, to zoom
        #'image-dpi': '1200',
        #'dpi': '1200',
    
    #     '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',
    } 

    config = pdfkit.configuration(wkhtmltopdf=r'xxxxx\wkhtmltopdf\bin\wkhtmltopdf.exe')
    try:
        pdfkit.from_string(str(html), title_name, configuration=config, options=options)
        print('Complete print: \n', url, ' : ', title_name, '\n=================================================')
    except IOError as err:
        print("IO error: {0}".format(err))
    except OSError as err:
        print("OS error: {0}".format(err))
    except ValueError:
        print("Could not convert data to an integer.")
    except:
        print("Unexpected error:", sys.exc_info()[0])
        raise
    else:
        print('Sleep 2s')
        time.sleep(2)



if __name__ == "__main__":
    path = r'C:\Users\Administrator\Desktop'
    os.chdir(path)
    txt_file = 'vx.txt'
    urls = txt_get_url(txt_file)
    
    folder = 'pdf'
    folder_temp = os.path.join(path, folder)
    if not os.path.isdir(folder_temp):
        os.mkdir(folder_temp)
    os.chdir(folder_temp)

    urls_ = [re.findall(r'[a-zA-z]+://[^s].*', x) for x in urls]

    for i in urls_:
        if i == []: continue
        #url = i.decode('utf-8').replace('\r', '').replace('\n', '').replace(' ', '')
        print('=================================================\n Printing url: ', i[0])
        url_pdf(i[0])
        time.sleep(1)

    print('Complete print!!')

李现在哪

感谢分享

huangfangding12

谢谢楼主分享

erda88

学习了多谢楼主分享

bsjasd

多谢楼主

蜉蝣天地

很方便，感谢楼主分享

青石板路

整挺好啊，莫名想起safari也可以另存为PDF

文西思密达

有什么方法可以批量提取公众号文章的链接？