Python 爬虫图片简单实现

# -*- coding=utf-8 -*-
import requests as req
from bs4 import BeautifulSoup
from PIL import Image
from io import BytesIO
import os
from skimage import io

url = "https://www.zhihu.com/question/37787176"
headers = {'User-Agent' : 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.96 Mobile Safari/537.36'}
response = req.get(url,headers=headers)
content = str(response.content)
#print content

soup = BeautifulSoup(content,'lxml')
images = soup.find_all('img')
print u"共有%d张图片" % len(images)

if not os.path.exists("images"):
  os.mkdir("images")

for i in range(len(images)):
  img = images[i]
  print u"正在处理第%d张图片..." % (i+1)
  img_src = img.get('src')
  if img_src.startswith("http"):
    ## use PIL
    '''
    print img_src
    response = req.get(img_src,headers=headers)
    image = Image.open(BytesIO(response.content))
    w,h = image.size
    print w,h
    img_path = "images/" + str(i+1) + ".jpg"
    if w>=500 and h>500:
      #image.show()
      image.save(img_path)

    '''

    ## use OpenCV
    import numpy as np
    import urllib
    import cv2

    resp = urllib.urlopen(img_src)

    image = np.asarray(bytearray(resp.read()), dtype="uint8")
    image = cv2.imdecode(image, cv2.IMREAD_COLOR)
    w,h = image.shape[:2]
    print w,h
    img_path = "images/" + str(i+1) + ".jpg"
    if w>=400 and h>400:
      cv2.imshow("Image", image)
      cv2.waitKey(3000)
      ##cv2.imwrite(img_path,image)

    ## use skimage

    ## image = io.imread(img_src)
    ## w,h = image.shape[:2]
    ## print w,h
    #io.imshow(image)
    #io.show()

    ## img_path = "images/" + str(i+1) + ".jpg"
    ## if w>=500 and h>500:
      ## image.show()
      ## image.save(img_path)
      ## io.imsave(img_path,image)

print u"处理完成！"