qiangqiang1 发表于 2020-5-17 14:07:41

新手求助 爬取煎蛋网报错 OSError

import re
import urllib.request
import os


def open_url(url):#设置访问对象
    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().decode('utf-8')
    return html


def get_img(html):   #获取图片
    p = r'<img src="([^"]+\.jpg")'
    imglist = re.findall(p,html)
    '''
    for each in imglist:
      print(each)
         '''
    for each in imglist:
      filename =each.split('/')[-1]
      print(filename)
#报错应该在这里
      pic = 'https:'+ each
      with open(filename, 'wb') as f:
            img = open_url(pic)
            f.write(img)

      
if __name__ == '__main__':
    url ='http://jandan.net/ooxx/MjAyMDAxMDMtNjk=#comments'
    get_img(open_url(url))

报错如下:
Traceback (most recent call last):
File "C:\Users\Administrator\Desktop\hello.py", line 32, in <module>
    get_img(open_url(url))
File "C:\Users\Administrator\Desktop\hello.py", line 25, in get_img
    with open(filename, 'wb') as f:
OSError: Invalid argument: '6e2a5d4dly1g10d7j3l6oj20j30rvq5q.jpg"'

如果不用图片的原名称,怎么定义图片的名称,比如从1开始取值

Twilight6 发表于 2020-5-17 14:23:23

本帖最后由 Twilight6 于 2020-5-17 14:58 编辑

你看看把代码改这样行不行的?
count = 0
    for each in imglist:
      count += 1
      filename = '%d.jpg' # 名字也是太多奇葩字符了 ,建议参照三楼所说,或者你爬个里面的专辑名?
      # 这边要改成http原因看下面截图
      pic = 'http:' + each
      with open(filename%count, 'wb') as f:
            img = open_url(pic)
            f.write(img)


qiuyouzhi 发表于 2020-5-17 14:24:13

你只要可以下载图片,你为啥非要让打开方式为filename呢?
可以自定义一个i,然后每次写入完i就+1

qiangqiang1 发表于 2020-5-17 15:52:58

Twilight6 发表于 2020-5-17 14:23
你看看把代码改这样行不行的?

这样写我遇到一个新的错误如下:Traceback (most recent call last):
File "C:\Users\Administrator\Desktop\hello.py", line 34, in <module>
    get_img(open_url(url))
File "C:\Users\Administrator\Desktop\hello.py", line 30, in get_img
    f.write(img)
TypeError: a bytes-like object is required, not 'str'
代码:import re
import urllib.request
import os


def open_url(url):#设置访问对象
    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().decode('utf-8',"replace")
    return html
   

def get_img(html):   #获取图片
    p = r'<img src="([^"]+\.jpg)'
    imglist = re.findall(p,html)
    '''
    for each in imglist:
      print(each)
         '''
    count = 0
    for each in imglist:
      count += 1
      filename = '%d.jpg'
      pic = 'http:' + each
      with open(filename%count, 'wb') as f:
            img = open_url(pic)
            f.write(img)
            
if __name__ == '__main__':
    url ='http://jandan.net/ooxx/MjAyMDAxMDMtNjk=#comments'
    get_img(open_url(url))

Twilight6 发表于 2020-5-17 15:58:26

qiangqiang1 发表于 2020-5-17 15:52
这样写我遇到一个新的错误如下:
代码:

    for each in imglist:
      count += 1
      filename = '%d.jpg'
      pic = 'http:' + each
      with open(filename % count, 'wb') as f:
            img = open_url(pic)
            f.write(img.encode())# 这边把 格式转回来就好

qiangqiang1 发表于 2020-5-17 16:57:28

Twilight6 发表于 2020-5-17 15:58


下载下来的图片无法打开,是不是编码格式的问题

Twilight6 发表于 2020-5-17 17:01:08

qiangqiang1 发表于 2020-5-17 16:57
下载下来的图片无法打开,是不是编码格式的问题

嗯,编码问题 在重新定义一个不用 decode()即可
import re
import urllib.request
import os


def open_url(url):# 设置访问对象
    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().decode('utf-8', "replace")
    return html

def open_url2(url):
    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):# 获取图片
    p = r'<img src="([^"]+\.jpg)'
    imglist = re.findall(p, html)
    '''
    for each in imglist:
      print(each)
         '''
    count = 0
    for each in imglist:
      count += 1
      filename = '%d.jpg'
      pic = 'http:' + each
      with open(filename % count, 'wb') as f:
            img = open_url2(pic)
            f.write(img)


if __name__ == '__main__':
    url = 'http://jandan.net/ooxx/MjAyMDAxMDMtNjk=#comments'
    get_img(open_url(url))

页: [1]
查看完整版本: 新手求助 爬取煎蛋网报错 OSError