python批量获取公众号图片生成PDF文件

一、获取公众号图片

需要安装的包
1、pip install bs4
2、pip install requests

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: KaiSun

import requests
from bs4 import BeautifulSoup
import re
import os

#获取网页信息
def getHTMLText(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except:
        return ""

#解析网页，获取所有图片url
def getimgURL(html):
    soup = BeautifulSoup(html , "html.parser")
    adlist=[]
    for i in soup.find_all("img"):
        try:
            ad= re.findall(r'.*src="(.*?)?" .*',str(i))
            if ad :
                adlist.append(ad)
        except:
            continue
    return adlist

#新建文件夹pic，下载并保存爬取的图片信息
def download(adlist):
    #注意更改文件目录
    root="/Users/sunkai/study_way/爬虫/picture/"
    for i in range(len(adlist)):
        path=root+str(i)+"."+'png'
        if not os.path.exists(root):
            os.mkdir(root)
        if not os.path.exists(path):
            if adlist[i][0]:
                r=requests.get(adlist[i][0])
                with open(path,'wb') as f:
                    f.write(r.content)
                    f.close()

def main():
    url = 'https://mp.weixin.qq.com/s/Jy5bUXb4aOmzEoPe6WODJA'
    html=getHTMLText(url)
    list=getimgURL(html)
    download(list)
main()

二、生成PDF文件

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: KaiSun


#  简单生成方式
import os

from reportlab.lib.pagesizes import A4, portrait, landscape
from reportlab.pdfgen import canvas

def convert_images_to_pdf(img_path, pdf_path):
    pages = 0
    (w, h) = portrait(A4)
    c = canvas.Canvas(pdf_path, pagesize = portrait(A4))
    l = os.listdir(img_path)
    l.sort(key= lambda x:int(x[:-4]))
    for i in l:
        f = img_path + os.sep + str(i)
        c.drawImage(f, 0, 0, w, h)
        c.showPage()
        pages = pages + 1
    c.save()

convert_images_to_pdf('/Users/sunkai/study_way/爬虫/picture/',
                      '/Users/sunkai/study_way/爬虫/result.pdf')

# 根据不同尺寸生成
import os, shutil
from PIL import Image
from reportlab.lib.pagesizes import A4, portrait, landscape
from reportlab.pdfgen import canvas
from PyPDF2 import PdfFileWriter, PdfFileReader
def convert_image_to_pdf(img_path, pdf_path):
    img = Image.open(img_path)
    (w0, h0) = img.size
    print(w0, h0)
    if w0 > h0:
        (w, h) = landscape(A4)
        c = canvas.Canvas(pdf_path, pagesize = landscape(A4))
        c.drawImage(img_path, 0, 0, w, h)
        c.showPage()
        c.save()
    else:
        (w, h) = portrait(A4)
        c = canvas.Canvas(pdf_path, pagesize = portrait(A4))
        c.drawImage(img_path, 0, 0, w, h)
        c.showPage()
        c.save()

def convert_images_to_pdf(img_path, pdf_path):
    pages = 0
    tmp_path = '.' + os.sep + 'temp'
    if not os.path.exists(tmp_path):
        os.mkdir(tmp_path)
    list = os.listdir(img_path)
    list.sort(key=lambda x:int(x[:-4]))
    output = PdfFileWriter()
    for item in list:
        img = img_path + os.sep + str(item)
        pdf = tmp_path + os.sep + str(pages + 1) + ".pdf"
        convert_image_to_pdf(img, pdf)
        input = PdfFileReader(open(pdf, "rb"))
        pageCount = input.getNumPages()
        pages = pages + 1
        for iPage in range(0, pageCount):
            output.addPage(input.getPage(iPage))
    outputStream = open(pdf_path, "wb")
    output.write(outputStream)
    outputStream.close()
    shutil.rmtree(tmp_path)


convert_images_to_pdf('/Users/sunkai/study_way/爬虫/picture/',
                      '/Users/sunkai/study_way/爬虫/result.pdf')