马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
爬虫煎蛋图片代码如下: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/60.0.3112.90 Safari/537.36')
response = urllib.request.urlopen(url)
html = response.read()
return html
def get_page(url):
html = url_open(url).decode('utf-8')
a = html.find('current-comment-page') + 23
b = html.find(']',a)
return html[a:b]
def find_imgs(url):
html = url_open(url).decode('utf-8')
img_addrs = []
a = html.find('img style="max-height: 750px; max-width: 480px;" src=')#检查元素后,得到的src在style后,这个如何处理?
while a != -1:
b = html.find('.jpg',a,a+255)
if b != -1:
img_addrs.append(html[a+53:b+4])
else:
b = a + 53
a = html.find('img style="max-height: 750px; max-width: 480px;" src=',b)
return img_addrs
def save_imgs(folder,img_addrs):
for each in img_addrs:
filename = each.split('/')[-1]
with open(filename,'wb') as f:
img = open_url(each)
f.write(img)
def download_mm(folder = 'mm',pages = 5):
os.mkdir(folder)
os.chdir(folder)
url = "http://jandan.net/ooxx/"
page_num = int(get_page(url))
for i in range(pages):
page_num -= i
page_url = url + 'page- ' + str(page_num) + '#comments'
img_addrs = find_imgs(page_url)
save_imgs(folder,img_addrs)
if __name__ == '__main__':
download_mm()
运行后报出来的错误如下:
报错信息
求指导,这是啥问题。谢谢啦 |