有关爬虫的问题
import urllib.requestimport re
def open_url(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/55.0.2883.87 Safari/537.36')
page=urllib.request.urlopen(req)
html=page.read().decode('utf-8')
return html
def get_img(html):
p=r'<img src="http://([^"]+\.jpg)'
imagelist=re.findall(p,html)#应用findall方法中，如果给出的re有子组，那么就会把子组的内容单个返回回来
#如果存在多个子组，将匹配的内容组合成元组 再返回
for each in imagelist:
print(each)
# filename=each.split("/")[-1]
# urllib.request.urlretrieve(each,filename,None)
if __name__=='__main__':
url="http://tieba.baidu.com/p/2354064447#!/l/p1"
get_img(open_url(url))
是这样的，我这样运行的时候程序是可以打印出字符串的
然而，当我调用urllib.request.urlretrieve(each,filename,None)方法后（也就是打印语句下面的两行）后，它就报错
错误信息：
C:\Users\qx\AppData\Local\Programs\Python\Python35-32\python.exe "F:/work place/pycharm/爬虫/get_img.py"
Traceback (most recent call last):
File "F:/work place/pycharm/爬虫/get_img.py", line 25, in <module>
get_img(open_url(url))
File "F:/work place/pycharm/爬虫/get_img.py", line 18, in get_img
urllib.request.urlretrieve(each,filename,None)
File "C:\Users\qx\AppData\Local\Programs\Python\Python35-32\lib\urllib\request.py", line 188, in urlretrieve
with contextlib.closing(urlopen(url, data)) as fp:
File "C:\Users\qx\AppData\Local\Programs\Python\Python35-32\lib\urllib\request.py", line 163, in urlopen
return opener.open(url, data, timeout)
File "C:\Users\qx\AppData\Local\Programs\Python\Python35-32\lib\urllib\request.py", line 451, in open
req = Request(fullurl, data)
File "C:\Users\qx\AppData\Local\Programs\Python\Python35-32\lib\urllib\request.py", line 269, in __init__
self.full_url = url
File "C:\Users\qx\AppData\Local\Programs\Python\Python35-32\lib\urllib\request.py", line 295, in full_url
self._parse()
File "C:\Users\qx\AppData\Local\Programs\Python\Python35-32\lib\urllib\request.py", line 324, in _parse
raise ValueError("unknown url type: %r" % self.full_url)
ValueError: unknown url type: 'imgsrc.baidu.com/forum/pic/item/bede9735e5dde711c981db20a0efce1b9f1661d5.jpg'
Process finished with exit code 1
页:
[1]