参考各路写了一个爬虫的代码，然而我怎么改都报AttributeError
代码如下：import base64
import urllib.request
import os
import time
import re
def get_pageurl(page,nums):
url_list = []
for i in range(nums):
temp1 = time.strftime('%Y%mYd',time.gmtime()) #获取当天的日期
temp2 = temp1 + str(int(page)-i) #获取页数
temp3 = base64.b64encode(temp2.encode()).decode() #base64转码
url = 'http://jandan.com/ooxx/' + temp3 + '#comments'
url_list.append(url)
return url_list
def get_html(url):
# 伪装电脑查询
req = urllib.request.Request(url)
req.add_header("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3314.0 Safari/537.36 SE 2.X MetaSr 1.0")
response = urllib.requset.urlopen(req)
html = response.read()
return html
def get_img(html):
html = html.decode('utf-8')
img_list = [] #创建列表用来保存图片地址
a = r'<img src="([^]+\.(jpg|gif))"' #使用正则表达式获取图片地址
img = re.findall(a,html)
#将每个地址塞入列表
for each in img:
img_list.append(each)
return img_list
def save_imgs(img_list):
for each in img_list:
img = get_html(each)
filename = each.split('/')[-1]
with open(filename,'wb') as f:
imge= open_url(each)
f.write(imge)
def download_mm():
os.mkdir('mmphoto')
os.chdir('mmphoto')
'''
x = int(input('请输入开始页码：'))
y = int(input('请输入下载多少页的图片：'))
'''
url_list = get_pageurl(130,2)
print(url_list)
for each in url_list:
html = get_html(each)
img_list = get_img(html)
save_imgs(img_list)
time.sleep(2)
print(each)
if __name__ == '__main__':
download_mm()
报错如下：
Traceback (most recent call last):
File "E:\新建文件夹\爬取煎蛋网妹子图.py", line 67, in <module>
download_mm()
File "E:\新建文件夹\爬取煎蛋网妹子图.py", line 60, in download_mm
html = get_html(each)
File "E:\新建文件夹\爬取煎蛋网妹子图.py", line 22, in get_html
response = urllib.requset.urlopen(req)
AttributeError: module 'urllib' has no attribute 'requset'
求大佬提出下问题所在
是 request 不是 requset
而且你代码有个open_url 不知道从何而来，代码中没有定义这个函数呀
本帖最后由 xiaosi4081 于 2020-7-21 16:53 编辑
import base64
import urllib.request
import os
import time
import re
def get_pageurl(page,nums):
url_list = []
for i in range(nums):
temp1 = time.strftime('%Y%mYd',time.gmtime()) #获取当天的日期
temp2 = temp1 + str(int(page)-i) #获取页数
temp3 = base64.b64encode(temp2.encode()).decode() #base64转码
url = 'http://jandan.com/ooxx/' + temp3 + '#comments'
url_list.append(url)
return url_list
def get_html(url):
# 伪装电脑查询
req = urllib.request.Request(url)
req.add_header("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3314.0 Safari/537.36 SE 2.X MetaSr 1.0")
response = urllib.request.urlopen(req)
html = response.read()
return html
def get_img(html):
html = html.decode('utf-8')
img_list = [] #创建列表用来保存图片地址
a = r'<img src="([^]+\.(jpg|gif))"' #使用正则表达式获取图片地址
img = re.findall(a,html)
#将每个地址塞入列表
for each in img:
img_list.append(each)
return img_list
def save_imgs(img_list):
for each in img_list:
img = get_html(each)
filename = each.split('/')[-1]
with open(filename,'wb') as f:
imge= open_url(each)
f.write(imge)
def download_mm():
os.mkdir('mmphoto')
os.chdir('mmphoto')
'''
x = int(input('请输入开始页码：'))
y = int(input('请输入下载多少页的图片：'))
'''
url_list = get_pageurl(130,2)
print(url_list)
for each in url_list:
html = get_html(each)
img_list = get_img(html)
save_imgs(img_list)
time.sleep(2)
print(each)
if __name__ == '__main__':
download_mm()
还有，你这个open_url从何处来?
页:
[1]