爬虫敏感图片的识别与过滤

sensitive_pic.py

from functools import reduce
from PIL import Image
import requests

# 计算pHash（只需要三行）:
def phash(img):
    img = img.resize((8, 8), Image.ANTIALIAS).convert('L')
    avg = reduce(lambda x, y: x + y, img.getdata()) / 64.
    return reduce(
        lambda x, y: x | (y[1] << y[0]),
        enumerate(map(lambda i: 0 if i < avg else 1, img.getdata())),
        0
    )

# 计算汉明距离:
def hamming_distance(a, b):
    return bin(a^b).count('1')

# 计算两个图片是否相似:
def is_imgs_similar(img1,img2):
	return True if hamming_distance(phash(img1),phash(img2)) <= 5 else False

# 打开本地存放一张敏感图片;
# 本次为了方便演示，从新浪图床拉下一张1024X1024的图片，保存命名为sensitive.jpg
sensitive_url="https://ws4.sinaimg.cn/large/006tNbRwgy1fwttj7bi36j30sg0sgwm0.jpg"
headers = {
        "User-Agent": "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5"}
pic = requests.get(sensitive_url, headers=headers, timeout=300)
if pic.status_code == 200:
    with open("sensitive.jpg", 'wb') as f:
        f.write(pic.content)
sensitive_pic = Image.open("sensitive.jpg")

# 爬虫获取的图片
target_url="https://ws3.sinaimg.cn/large/006tNbRwgy1fwttsauo6jj30h80han0y.jpg"
pic = requests.get(target_url, headers=headers, timeout=300)
if pic.status_code == 200:
    with open("target.jpg", 'wb') as f:
        f.write(pic.content)
target_pic = Image.open("target.jpg")

# 判断爬虫获取的图片和敏感图片是否相似
if is_imgs_similar(target_pic, sensitive_pic):
    print("2张图片相似,替换敏感图片为”优雅的python“:{}".format("https://ws2.sinaimg.cn/large/006tNbRwgy1fw9yjmot3uj30y60y6q40.jpg"))
else:
    print("不相似")