python 圖檔爬取

import re

import urllib.request

import chardet

from lxml import etree

from bs4 import BeautifulSoup

url = "https://www.qiushibaike.com/pic/"

header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:60.0) Gecko/20100101 Firefox/60.0",

"Referer":"https://www.qiushibaike.com/"}

def fun(a,b,c):

    precent = a*b*1.0/c

    if precent>1:

    precent = 1

    else:

    print("%.2f"%(precent*100)+'%')

    #a:已經下載下傳的子產品

    #b:資料塊的大小

    #c:遠端檔案的大小

req = urllib.request.Request(url,data = None,headers = header)

ope = urllib.request.urlopen(req)

html = ope.read().decode("utf-8")

reg = r'src="(.+?\.jpeg)"'

img = re.compile(reg)

condition = re.findall(img,html)

for imgurl in condition:

imgurl = 'https:'+imgurl

imgname = imgurl.rsplit('/',1)

urllib.request.urlretrieve(imgurl,imgname[1],fun)