Python 处理网站中 src="data:image/png;base64, ...... 的图片

 

第一次遇到这样的情况 记录下

 

 

 

处理代码

# 先把图片的html粘过来
png_html= '''<img
        src="data:image/png;base64,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"
        class="img_number d0c93665f22f1ac3ce83ee13bd8e8baf" style="left:11.5px">
        '''

# 读取src属性
from lxml import etree
html = etree.HTML(png_html)
img = html.xpath('//img')[0]
img_src = img.xpath('./@src')[0]
img_src = img_src.replace('data:image/png;base64,' , '')
print('处理后的文本' , img_src)


import  base64
# 编码转换
image_byte = base64.b64decode(img_src)  # base64编码，类型 byte
print('编码转换' , image_byte)


# 保存到本地
with open('pic.png' ,'ab') as f:
    f.write(image_byte)

# 使用ocr识别
import ddddocr
ocr = ddddocr.DdddOcr()
print(ocr.classification(image_byte))