python爬取微信公众号文章图片并转为PDF

Thadea ·

更新时间:2024-11-13

· 980 次阅读

遇到那种有很多图的微信公众号文章咋办？一个一个存很麻烦，应朋友的要求自己写了个爬虫。
2.0版本完成了！完善了生成pdf的功能，可根据图片比例自动调节大小，防止超出页面范围，增加了序号方面查看

#-----------------settings---------------
#url='https://mp.weixin.qq.com/s/8JwB_SXQ-80uwQ9L97BMgw'
print('jd3096 for king 2.0 VIP8钻石永久会员版')
print('愿你远离流氓软件每一天')
url=input('请输入网址：')
#-----------------get data----------------
import requests
import re
from bs4 import BeautifulSoup
import os
from PIL import Image
try:
    os.makedirs('pics')
except:
    pass
os.chdir('pics')
page=requests.get(url).text
soup = BeautifulSoup(page, 'html.parser')
jdata = soup.find_all('img')
pn=0
for i in jdata:
    try:
        src=i['data-src']
        print(src)
        rp = requests.get(src)
        with open(str(pn)+'.jpg','wb+')as f : # 循环写入图片
            print(str(pn)+'.jpg')
            f.write(rp.content)
        pn+=1
    except:
        pass
#--------------------make pdf--------------------
from fpdf import FPDF
import os
path=os.getcwd()
print(path)
pdf = FPDF()
pdf.set_auto_page_break(1)
imagelist = [i for i in os.listdir()]
imagelist.sort(key=lambda x: int(x.split('.')[0]))
print(imagelist)
for image in imagelist:
    try:
        img = Image.open(image)
        w = img.width       #图片的宽
        h = img.height      #图片的高
        ii=h/w
        print(ii)
        if ii>1.41:
            ww=int(250/ii)
            pdf.add_page()
            pdf.set_xy(0,0)
            pdf.set_font('arial','B',14)
            pdf.cell(60)
            pdf.cell(70,10,image,border=0, ln=1, align='C')
            pdf.image(os.path.join(path, image), w=ww, h=250)
        else:
            hh=int(180*ii)
            pdf.add_page()
            pdf.set_xy(0,0)
            pdf.set_font('arial','B',14)
            pdf.cell(60)
            pdf.cell(70,10,image,border=0, ln=1, align='C')
            pdf.image(os.path.join(path, image), w=180, h=hh)
    except:
        pass
pdf.output(os.path.join(path, "merge.pdf"), "F")

爬完了长这样：