来个 大佬帮忙指导一下
不知道怎么 解决 这种 错误==================================================================
import urllib.request
import os
def open_html(url):
res = urllib.request.Request(url)
res.add_header('User-Agent',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36')
respones = urllib.request.urlopen(res)
html = respones.read()
return html
def get_num(url):
res = urllib.request.Request(url)
res.add_header('User-Agent',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36')
respones = urllib.request.urlopen(res)
html = respones.read().decode('utf-8')
# print(html)
a = html.find('index-') + 6
b = html.find('\.',a)
return html
def find_adds(url):
res = urllib.request.Request(url)
res.add_header('User-Agent',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36')
respones = urllib.request.urlopen(res)
html = respones.read().decode('utf-8')
print(html)
img_adds = []
a = html.find('img src=')
b = html.find('.jpg', a)
if b != -1:
img_adds.append(html)
while a != -1:
b = html.find('.jpg',a)
print(b)
if b != -1:
img_adds.append(html)
else:
b = a + 9
a = html.find('img src=',b)
# print(img_adds)
return img_adds
def save_img(mm,img_adds):
for adds in img_adds:
img_name = adds.split('/')[-1]
with open(img_name, 'wb') as f:
img = open_html(adds)
f.write(img)
def mmmm(mm='tutu',pages=5):
os.mkdir(mm)
os.chdir(mm)
url = 'https://www.4493.com/star/meizi/'
num = int(get_num(url))
for i in range(pages):
num -= i
get_url = url + 'a/more_' + str(num) + '.html'
img_adds = find_adds(get_url)
save_img(mm,img_adds,)
if __name__ == '__main__':
mmmm() html = respones.read().decode('gb2312')
ba21 发表于 2017-12-21 23:09
html = respones.read().decode('gb2312')
试试 先谢谢大佬
页:
[1]