爬虫：代码没有报错，但是文件夹下没有图片
代码如下：import urllib.request
import os
def url_open(url):
req = urllib.request.Request(url)
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.19041')
respone = urllib.request.urlopen(req)
html = respone.read()
return html
def find_img(url):
html = url_open(url).decode('utf-8')
img_addrs = []
a = html.find('src=')
while a != -1:
b = html.find('.jpg',a,a+255)
if b != -1:
html2 = 'http:'+html
img_addrs.append(html2)
else:
b = a+5
a = html.find('src=',b)
return(img_addrs)
def save_img(folder,img_addrs):
for each in img_addrs:
filename = each.split('/')[-1]
with open(filename,'wb') as f:
img = url_open(each)
f.write(img)
def download_ww(folder = 'pic'):
os.mkdir(folder)
os.chdir(folder)
url = 'http://jandan.net/pic/'
for i in range(3):
page_url = url +'MjAyMDEyMTUtMTk'+str(i)+'#comments'
img_addrs = find_img(page_url)
save_img(folder,img_addrs)
if __name__ == '__main__':
download_ww()
代码没有报错，但是文件夹下没有图片，请问是什么问题{:10_266:} # _*_ coding: utf-8 _*_
import urllib.request
import re
import os
def ck_dir(folder='pic'):
if not os.path.exists(folder):
os.mkdir(folder)
os.chdir(folder)
def main():
ck_dir()
url = 'http://jandan.net/pic'
for i in range(3):
req = urllib.request.Request(url)
req.add_header('user-agent', 'mozilla')
r = urllib.request.urlopen(req)
html = r.read().decode('utf-8')
result = re.findall(r'<img src="(.*?)"', html)
nx_page = re.findall(r'href="(.*?)" class="previous', html)
url = 'http:' + nx_page
dl_img(result)
def dl_img(ls):
for item in ls:
img_url = 'http:' + item
img_name = item.split('/')[-1]
urllib.request.urlretrieve(img_url, img_name)
if __name__ == '__main__':
main()
页:
[1]