煎蛋网爬虫遇到的问题 urllib.error.URLError: <urlopen error no host given>

xiangtao

采用与鱼c课程基本相同的代码，只修改爬图的网址和页码循环的逻辑，爬 jandan.net/zoo 和 jandan.net/pic 都成功了，但是爬 jandan.net/ooxx 遇到问题，可以爬百来张，如果网站上发了新图也可以被爬下来，但是基本每次都在一个相同的位置停止报错：urllib.error.URLError: <urlopen error no host given>

代码如下：
import urllib.request
import os
import base64
import random

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:73.0) Gecko/20100101 Firefox/73.0')

    # porxies = ['183.146.213.157:80', '39.106.114.143:80', '101.4.136.34:81']
    # proxy = random.choice(porxies)
    #
    # proxy_support = urllib.request.ProxyHandler({'http':proxy})
    # opener = urllib.request.build_opener(proxy_support)
    # urllib.request.install_opener(opener)


    response = urllib.request.urlopen(url)
    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(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_animal(folder='jiandan_ooxx'):
    os.mkdir(folder)
    os.chdir(folder)

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

    while page_num != 0:
        page_index = str(base64.b64encode(('20200217-' + str(page_num)).encode('utf-8')), 'utf-8')  #对网址进行base64编码
        page_url = url + page_index + '#comments'
        img_addrs = find_imgs(page_url)
        save_imgs(img_addrs)
        page_num -= 1


if __name__ == '__main__':
    download_animal()






报错：
Traceback (most recent call last):
  File "C:/python_pycharm/test.py", line 71, in <module>
    download_animal()
  File "C:/python_pycharm/test.py", line 66, in download_animal
    save_imgs(img_addrs)
  File "C:/python_pycharm/test.py", line 52, in save_imgs
    img = url_open(each)
  File "C:/python_pycharm/test.py", line 18, in url_open
    response = urllib.request.urlopen(url)
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 222, in urlopen
    return opener.open(url, data, timeout)
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 522, in open
    req = meth(req)
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 1243, in do_request_
    raise URLError('no host given')
urllib.error.URLError: <urlopen error no host given>

Process finished with exit code 1

dlnb526

大概率是电脑的代理设置有问题，推荐你通过try except 语句来跳过错误使爬虫继续。
希望可以帮助到你