大佬们为啥0基础python里面正则表达式爬贴吧下载图片的现在已经用不了了
import urllib.requestimport 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/83.0.4103.106 Safari/537.36')
page = urllib.request.urlopen(req)
html = page.read().decode('utf-8')
return html
def get_img(html):
p = r'<img class="BDE_Image" src=("[^"]+\.jpg")'
imglist = re.findall(p, html)
'''
for each in imglist:
print(each)
'''
try:
os.mkdir('NewPics')
except FileExistsError:
# 如果文件夹已存在则覆盖保存！
pass
os.chdir('NewPics')
for each in imglist:
filename = each.split("/")[-1]
urllib.request.urlretrieve(each, filename, None)
if __name__ == '__main__':
url = 'https://tieba.baidu.com/p/6747778991'
get_img(open_url(url))
这个是代码 Traceback (most recent call last):
File "I:\Python\爬取贴吧.py", line 35, in <module>
get_img(open_url(url))
File "I:\Python\爬取贴吧.py", line 31, in get_img
urllib.request.urlretrieve(each, filename, None)
File "I:\Python\lib\urllib\request.py", line 247, in urlretrieve
with contextlib.closing(urlopen(url, data)) as fp:
File "I:\Python\lib\urllib\request.py", line 222, in urlopen
return opener.open(url, data, timeout)
File "I:\Python\lib\urllib\request.py", line 525, in open
response = self._open(req, data)
File "I:\Python\lib\urllib\request.py", line 548, in _open
'unknown_open', req)
File "I:\Python\lib\urllib\request.py", line 503, in _call_chain
result = func(*args)
File "I:\Python\lib\urllib\request.py", line 1387, in unknown_open
raise URLError('unknown url type: %s' % type)
urllib.error.URLError: <urlopen error unknown url type: "http>
运行之后提示这个 有人吗
p = r'<img class="BDE_Image" src="(.*?\.jpg)"'
页:
[1]