Chilkat2-Python

Extract data:image/png;base64 from HTML

See more Base64 Examples

Demonstrates how to extract base64 image data from HTMl and save to files. Chilkat2-Python

import chilkat2

success = False

sb = chilkat2.StringBuilder()
bd = chilkat2.BinData()
sbFilename = chilkat2.StringBuilder()
index = 1

success = sb.LoadFile("qa_data/html/oresp body.txt","utf-8")
# Assume success.
print("length = " + str(sb.Length))

mayHaveMore = True
while mayHaveMore == True :

    # Get the base64 between the 1st occurrence "data:image/png;base64," and "'"
    sBase64 = sb.GetBetween("data:image/png;base64,","'")

    # If nothing is found, then we'll exit the loop because there are no more.
    mayHaveMore = sb.LastMethodSuccess

    if (sb.LastMethodSuccess == True):
        # Found something.
        # Load into bd and save.
        success = bd.LoadEncoded(sBase64,"base64")

        sbFilename.SetString("qa_output/png_")
        sbFilename.AppendInt(index)
        sbFilename.Append(".png")

        bd.WriteFile(sbFilename.GetAsString())

        # Replace "data:image/png;base64" with "data:image-png;base64" so the next iteration finds the next occurrence.
        sb.ReplaceFirst("data:image/png;base64","data:image-png;base64")

    index = index + 1

# Restore our replacements..
count = sb.Replace("data:image-png;base64","data:image/png;base64")

print("All done.")