写出的爬图py老是出错，请指正
本帖最后由 huahua_0917 于 2020-4-5 15:54 编辑根据小甲鱼书上和网站视频讲述，完全复制的代码，但是为什么会出错？
代码如下：
import urllib.request
import re
import os
def open_url(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/80.0.3987.149 Safari/537.36')
page = urllib.request.urlopen(req)
html = page.read().decode('utf-8')
return html
def get_image(url):
p = r'<img class="BDE_Image".*？src="[^"]*\.jpg".*?>'
imagelist = re.findall(p, html)
try:
os.mkdir("NewPics")
except FileExistsError:
pass
os.chdir("NewPics")
'''
for each in imagelist:
print(each)
'''
for each in imagelist:
filename = each.split("/")[-1]
urllib.request.urlretrieve(each, filename, None)
if __name__ == '__main__':
url = "https://tieba.baidu.com/p/6426975446"
get_image(open_url(url))
提示以下错误：
Traceback (most recent call last):
File "C:\Users\huahua\Desktop\python\download_p.py", line 37, in <module>
get_image(open_url(url))
File "C:\Users\huahua\Desktop\python\download_p.py", line 18, in get_image
imagelist = re.findall(p, html)
NameError: name 'html' is not defined
为什么不贴错误信息呢 这样试试：
import urllib.request
import re
import os
def open_url(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/80.0.3987.149 Safari/537.36')
page = urllib.request.urlopen(req)
html = page.read().decode('utf-8')
return html
def get_image(html):
p = r'<img class="BDE_Image".*？src="[^"]*\.jpg".*?>'
imagelist = re.findall(p, html)
try:
os.mkdir("NewPics")
except FileExistsError:
pass
os.chdir("NewPics")
for each in imagelist:
filename = each.split("/")[-1]
urllib.request.urlretrieve(each, filename, None)
if __name__ == '__main__':
url = "https://tieba.baidu.com/p/6426975446"
get_image(open_url(url))
页:
[1]