[已解决]【求助】煎蛋爬妹子图程序出现不知名错误

二农戏猪`

import urllib.request
import os
import base64
import re

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36')
    response = urllib.request.urlopen(req)
    html = response.read()
    print(html)
   
    return html

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

    a = r'<span class="current-comment-page">\[(\d+)\]</span>'
    page_list = re.findall(a,html)

    for each in page_list:
        t = each

    return t

      
def base_num(page_num):
    times = '20200811-' + str(page_num)
    s = times.encode('utf-8')
    sw = base64.b64encode(s)
    str_sw = str(sw)
    string = str_sw.split("'")[-1]
    print (string)
    return string


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


    a = r'<img src="([^"]+\.jpg)"'
    b = re.findall(a,html)
   
    if not len(b):
        pic_url_list.append(b)

    for each in pic_url_list:
        print(each)

        
def save_pic(folder, pic_url):
    pass

def download_mm(folder = 'mm', pages = 10):
    #创建一个文件夹
    os.mkdir(folder)
    os.chdir(folder)

    url = 'http://jandan.net/ooxx/'
    #获取页码
    page_num = int(get_page(url))

    for i in range(pages):
        page_num -=i
        #base64加密
        x = base_num(page_num)
        #获取页码地址
        page_url = url + x + '#comments'
        #获取图片具体地址并保存成列表
        pic_url = find_pic_url(page_url)
        save_pic(folder, pic_url)

        
if __name__ == '__main__':
    download_mm()


我这个到底哪里出错我也拿不准，求大神

最佳答案

月排行榜 / 总排行榜

suchocolate

2020-8-15 11:22:56

不用xpath或bs太低效了

import requests

from lxml import etree

import os





def ck_dir():

    # Please fill in the name of the path where you want to save the images

    pic_dir = 'mm'

    if not os.path.exists(pic_dir):

        os.mkdir(pic_dir)

    os.chdir(pic_dir)





def get_pic_url(act_url):

    r = requests.get(act_url, headers=headers)

    html = etree.HTML(r.text)

    # pic list

    result = html.xpath('//img/@src')

    # last pic is not mm pic

    result.pop()

    # next page url

    act_nx_pg = html.xpath('//a[contains(text(),"99")]/@href')[zxsq-anti-bbcode-0]

    return result, act_nx_pg





def main():

    # pic counter

    n = 1

    # check pic directory

    ck_dir()

    # pic url list

    pic_list = []

    # next page url

    nx_pg_url = ''

    # get pics urls

    for item in range(100, 98, -1):

        if item == 100:

            pic_url, nx_pg = get_pic_url(url)

        else:

            pic_url, nx_pg = get_pic_url(nx_pg_url)

        nx_pg_url = f'{url}/{nx_pg}#comments'

        pic_list.extend(pic_url)

    # download pics

    for item in pic_list:

        r = requests.get('http:' + item, headers=headers)

        pic_name = item.split('/')[-1]

        with open(pic_name, 'wb') as f:

            f.write(r.content)

            print(f'{pic_name} has been downloaded. total number: {n}')

            n = n + 1





if __name__ == '__main__':

    # global variables

    url = 'http://jandan.net/ooxx'

    headers = {'User-agent': 'firefox'}

    # main func

    main()

跳转到最佳答案楼层

1q23w31

报错信息是啥

weiter

煎蛋的妹子图还有？？？
弹幕上都说煎蛋的图没了……

Twilight6

是因为你没有把创建的文件夹删除吧，把你代码下 mm 文件夹删除即可，然后代码就正常运行了

二农戏猪`

Twilight6 发表于 2020-8-11 18:35
是因为你没有把创建的文件夹删除吧，把你代码下 mm 文件夹删除即可，然后代码就正常运行了

不是，我知道这个错误 它一直刷新Squeezed text (884lines)

二农戏猪`

1q23w31 发表于 2020-8-11 18:29
报错信息是啥

Squeezed text (884lines)

1q23w31

二农戏猪` 发表于 2020-8-11 20:27
Squeezed text (884lines)

点开它

二农戏猪`

weiter 发表于 2020-8-11 18:34
煎蛋的妹子图还有？？？
弹幕上都说煎蛋的图没了……

有 叫随手拍

二农戏猪`

1q23w31 发表于 2020-8-11 20:29
点开它

我就卡了

1q23w31

二农戏猪` 发表于 2020-8-11 20:36
我就卡了

import urllib.request
import os
import base64
import re


def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent',
                   'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36')
    response = urllib.request.urlopen(req)
    html = response.read()
    #print(html)

    return html


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

    a = r'<span class="current-comment-page">\[(\d+)\]</span>'
    page_list = re.findall(a, html)

    for each in page_list:
        t = each

    return t


def base_num(page_num):
    times = '20200811-' + str(page_num)
    s = times.encode('utf-8')
    sw = base64.b64encode(s)
    str_sw = str(sw)
    string = str_sw.split("'")[-1]
    print(string)
    return string


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

    a = r'<img src="([^"]+\.jpg)"'
    b = re.findall(a, html)

    if not len(b):
        pic_url_list.append(b)

    for each in pic_url_list:
        print(each)


def save_pic(folder, pic_url):
    pass


def download_mm(folder='mm', pages=10):
    # 创建一个文件夹
    os.mkdir(folder)
    os.chdir(folder)

    url = 'http://jandan.net/ooxx/'
    # 获取页码
    page_num = int(get_page(url))

    for i in range(pages):
        page_num -= i
        # base64加密
        x = base_num(page_num)
        # 获取页码地址
        page_url = url + x + '#comments'
        # 获取图片具体地址并保存成列表
        pic_url = find_pic_url(page_url)
        save_pic(folder, pic_url)


if __name__ == '__main__':
    download_mm()

看起来，你的代码没完成，程序没问题，继续写吧（已修改）

二农戏猪`

1q23w31 发表于 2020-8-11 21:17
看起来，你的代码没完成，程序没问题，继续写吧（已修改）

好，我试试，谢谢啦

二农戏猪`

1q23w31 发表于 2020-8-11 21:17
看起来，你的代码没完成，程序没问题，继续写吧（已修改）

还是不行啊

1q23w31

二农戏猪` 发表于 2020-8-11 21:31
还是不行啊

？？

二农戏猪`

1q23w31 发表于 2020-8-11 21:31
？？

我写完了 还是没下载

1q23w31

二农戏猪` 发表于 2020-8-11 21:34
我写完了 还是没下载

把写完的发一下

二农戏猪`

1q23w31 发表于 2020-8-11 21:35
把写完的发一下

import urllib.request
import os
import base64
import re

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36')
    response = urllib.request.urlopen(req)
    html = response.read()
    print(html)
   
    return html

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

    a = r'<span class="current-comment-page">\[(\d+)\]</span>'
    page_list = re.findall(a,html)

    for each in page_list:
        t = each

        return t

      
def base_num(page_num):
    times = '20200811-' + str(page_num)
    s = times.encode('utf-8')
    sw = base64.b64encode(s)
    str_sw = str(sw)
    string = str_sw.split("'")[-1]
   
    return string


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


    a = r'<img src="([^"]+\.jpg)"'
    b = re.findall(a,html)
   
    if not len(b):
        pic_url_list.append(b)

    return pic_url_list

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

def download_mm(folder = 'mm', pages = 10):
    #创建一个文件夹
    os.mkdir(folder)
    os.chdir(folder)

    url = 'http://jandan.net/ooxx/'
    #获取页码
    page_num = int(get_page(url))

    for i in range(pages):
        page_num -=i
        #base64加密
        x = base_num(page_num)
        #获取页码地址
        page_url = url + x + '#comments'
        #获取图片具体地址并保存成列表
        pic_url = find_pic_url(page_url)
        save_pic(folder, pic_url_list)

        
if __name__ == '__main__':
    download_mm()

二农戏猪`

1q23w31 发表于 2020-8-11 21:35
把写完的发一下

iimport urllib.request
import os
import base64
import re

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36')
    response = urllib.request.urlopen(req)
    html = response.read()
    print(html)
   
    return html

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

    a = r'<span class="current-comment-page">\[(\d+)\]</span>'
    page_list = re.findall(a,html)

    for each in page_list:
        t = each

    return t

      
def base_num(page_num):
    times = '20200811-' + str(page_num)
    s = times.encode('utf-8')
    sw = base64.b64encode(s)
    str_sw = str(sw)
    string = str_sw.split("'")[-1]
   
    return string


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


    a = r'<img src="([^"]+\.jpg)"'
    b = re.findall(a,html)
   
    if not len(b):
        pic_url.append(b)

    return pic_url

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

def download_mm(folder = 'mm', pages = 10):
    #创建一个文件夹
    os.mkdir(folder)
    os.chdir(folder)

    url = 'http://jandan.net/ooxx/'
    #获取页码
    page_num = int(get_page(url))

    for i in range(pages):
        page_num -=i
        #base64加密
        x = base_num(page_num)
        #获取页码地址
        page_url = url + x + '#comments'
        #获取图片具体地址并保存成列表
        pic_url = find_pic_url(page_url)
        save_pic(folder, pic_url)

        
if __name__ == '__main__':
    download_mm()

二农戏猪`

import urllib.request
import os
import base64
import re

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36')
    response = urllib.request.urlopen(req)
    html = response.read()
    print(html)
   
    return html

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

    a = r'<span class="current-comment-page">\[(\d+)\]</span>'
    page_list = re.findall(a,html)

    for each in page_list:
        t = each

    return t

      
def base_num(page_num):
    times = '20200811-' + str(page_num)
    s = times.encode('utf-8')
    sw = base64.b64encode(s)
    str_sw = str(sw)
    string = str_sw.split("'")[-1]
   
    return string


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


    a = r'<img src="([^"]+\.jpg)"'
    b = re.findall(a,html)
   
    if not len(b):
        pic_url.append(b)

    return pic_url

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

def download_mm(folder = 'mm', pages = 10):
    #创建一个文件夹
    os.mkdir(folder)
    os.chdir(folder)

    url = 'http://jandan.net/ooxx/'
    #获取页码
    page_num = int(get_page(url))

    for i in range(pages):
        page_num -=i
        #base64加密
        x = base_num(page_num)
        #获取页码地址
        page_url = url + x + '#comments'
        #获取图片具体地址并保存成列表
        pic_url = find_pic_url(page_url)
        save_pic(folder, pic_url)

        
if __name__ == '__main__':
    download_mm()

二农戏猪`

需要审核

二农戏猪`

1q23w31 发表于 2020-8-11 21:35
把写完的发一下

import urllib.request
import os
import base64
import re

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36')
    response = urllib.request.urlopen(req)
    html = response.read()
    print(html)
    
    return html

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

    a = r'<span class="current-comment-page">\[(\d+)\]</span>'
    page_list = re.findall(a,html)

    for each in page_list:
        t = each

        return t

      
def base_num(page_num):
    times = '20200811-' + str(page_num)
    s = times.encode('utf-8')
    sw = base64.b64encode(s)
    str_sw = str(sw)
    string = str_sw.split("'")[-1]
    
    return string


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


    a = r'<img src="([^"]+\.jpg)"'
    b = re.findall(a,html)
    
    if not len(b):
        pic_url.append(b)

    return pic_url

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

def download_mm(folder = 'mm', pages = 10):
    #创建一个文件夹
    os.mkdir(folder)
    os.chdir(folder)

    url = 'http://jandan.net/ooxx/'
    #获取页码
    page_num = int(get_page(url))

    for i in range(pages):
        page_num -=i
        #base64加密
        x = base_num(page_num)
        #获取页码地址
        page_url = url + x + '#comments'
        #获取图片具体地址并保存成列表
        pic_url = find_pic_url(page_url)
        save_pic(folder, pic_url)

        
if __name__ == '__main__':
    download_mm()