python3 crawling picture example code
- 2021-01-22 05:16:07
- OfStack
The specific code is as follows:
#coding=utf8
from urllib import request
import re
import urllib,os
url='http://tieba.baidu.com/p/3840085725'
def get_image(url):
# Get the page source code
page = urllib.request.urlopen(url)
html = page.read()
# Decode, otherwise report an error
html = html.decode('utf8')
# The regular match gets the content of ()
reg = r'src="(https.+?.[jpg,png])"'
imge = re.compile(reg)
# Get regular matched data, "(.+?.jpg)" The data is returned 1 a list
imglist = imge.findall(html)
return imglist
def save_img(imglist):
dir = os.path.join(os.path.dirname(__file__),'img')
i=1
for img in imglist:
#python3 Formatts another string 1 Kind of writing
imgpath = f'{dir}\\image{i}.jpg'
try:
#urlretrieve Download the image and save it locally
urllib.request.urlretrieve(img,imgpath)
i += 1
print(u' Image starts to download ')
except Exception:
print(f'image:{img} Download failed ')
continue
imglist = get_image(url)
save_img(imglist)
conclusion