初学爬虫 为什么爬下的的图片无法打开，

[jungle_yao]

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; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.89 Safari/537.36")
# response = urllib.request.urlopen(req)
# html = response.read()
# return html

data = None
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36'}
req = urllib.request.Request('http://jandan.net/ooxx', data, headers)
response = urllib.request.urlopen(req)
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)
print(html[a:b])
return html[a:b]


def find_imgs(url):
html = url_open(url).decode("utf-8")
img_addrs = []

a = html.find('img src=')

while a != -1:

b = html.find('.jpg', a, a + 255)
if b != -1:
img_addrs.append(html[a + 9:b + 4])
else:
b = a + 9

a = html.find('img 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 = url_open(each)
f.write(img)
f.close


def download_mm(folder="xxxx", pages=10):
if not os.path.isdir(folder):
os.mkdir(folder)
os.chdir(folder)
else:
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()

爬下来的图片都是损坏的。但是却可以用 记事本打开。

[chuifengde]

把你保存图片的代码改成这句：urllib.request.urlretrieve('http:'+each,filename)

• 打赏
• 举报

回复 赞