[已解决]问题求助

小尤you

煎蛋网爬取图片不成功该怎么解决？
代码如下：

import urllib.request
import os

def url_open(url):
    data=None
    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/49.0.2623.75 Safari/537.36 LBBROWSER')
    response = urllib.request.urlopen(req)
    html = response.read()

    return html

def get_page(url):
    html = url_open(url).decode('utf-8')

    a = html.find('current-comment-page') + 23
    b = html.find(']',a)

    return html[a:b]
    

def find_imgs(url):
    html = url_open(url).decode('utf-8')
    img_addrs = []

    a = html.find('img src=')

    while a != -1:
        b = html.find('.jpg',a,a+255)
        if b !=-1:
            img_addrs.append('http:' + html[a+9:b+4])
        else:
            b =a + 9

        a = html.find('img src=',b)

    return img_addrs

        
def save_imgs(folder,img_addrs):
    for each in img_addrs:
        filename = each.split('/')[-1]
        with open(filename,'wb') as f:
            img = url_open(each)
            f.write(img)
            

def download_mm(folder='OOXX',pages=10):
    os.mkdir(folder)
    os.chdir(folder)

    url = "http://jandan.net/ooxx/"
    page_num = int(get_page(url))

    for i in range(pages):
        page_num -= i
        page_url = url + 'page-' + str(page_num) + '#comments'
        img_addrs = find_imgs(page_url)
        save_imgs(folder,img_addrs)
        time.sleep(10)

if __name__ == '__main__':
    download_mm()

报错如下
Traceback (most recent call last):
  File "E:\Python学习\小甲鱼课上\下载妹子图.py", line 63, in <module>
    download_mm()
  File "E:\Python学习\小甲鱼课上\下载妹子图.py", line 58, in download_mm
    img_addrs = find_imgs(page_url)
  File "E:\Python学习\小甲鱼课上\下载妹子图.py", line 23, in find_imgs
    html = url_open(url).decode('utf-8')
  File "E:\Python学习\小甲鱼课上\下载妹子图.py", line 8, in url_open
    response = urllib.request.urlopen(req)
  File "E:\python\lib\urllib\request.py", line 222, in urlopen
    return opener.open(url, data, timeout)
  File "E:\python\lib\urllib\request.py", line 531, in open
    response = meth(req, response)
  File "E:\python\lib\urllib\request.py", line 641, in http_response
    'http', request, response, code, msg, hdrs)
  File "E:\python\lib\urllib\request.py", line 569, in error
    return self._call_chain(*args)
  File "E:\python\lib\urllib\request.py", line 503, in _call_chain
    result = func(*args)
  File "E:\python\lib\urllib\request.py", line 649, in http_error_default
    raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 404: Not Found

最佳答案

月排行榜 / 总排行榜

Twilight6

2020-8-1 10:43:45

现在煎蛋网不是直接拿数字当页码了，建议你学了正则然后去爬链接吧，这里举个爬一个图库的例子：

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()
    return html


def get_img(html):  # 获取图片
    p = r'<img src="([^"]+\.jpg)'
    imglist = re.findall(p, html.decode('utf-8', "replace"))
    '''
    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))

跳转到最佳答案楼层

Twilight6

现在煎蛋网不是直接拿数字当页码了，建议你学了正则然后去爬链接吧，这里举个爬一个图库的例子：

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()
    return html


def get_img(html):  # 获取图片
    p = r'<img src="([^"]+\.jpg)'
    imglist = re.findall(p, html.decode('utf-8', "replace"))
    '''
    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))