使用Python爬取煎蛋网妹纸图片
import urllib.requestimport os
import os.path
import re
def dir(dir_name="images"):
"""设定图片保存目录,基于当前程序运行目录"""
if os.path.isdir(dir_name):
os.chdir(dir_name)
else:
os.mkdir(dir_name)
os.chdir(dir_name)
def saveImage(img, url):
"""保存图片方法"""
respones = urllib.request.urlopen(url)
image = respones.read()
with open(img, "wb") as f:
f.write(image)
def getURL():
page_list = []
"""
可使用列表推导式，这里主要是定义页面的数量，数量越多图片越多
page_list =
"""
for i in range(1,5):
page_list.append(i)
return page_list
def getResposen():
"""获取url并对url进行处理，然后保存图片"""
page_list = getURL()
for i in page_list:
res = "http://jandan.net/ooxx/page-"+str(i)+"#comments"
respones = urllib.request.urlopen(res)
html = respones.read()
html = html.decode("utf-8")
jpg_url = re.findall(r'<img src=.+?\.jpg', html)
for j in jpg_url:
s = "http://"+j.split('//')
saveImage(s.split("/")[-1],s)
dir()
getURL()
getResposen()
页:
[1]