[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

1. 
   
2. 
   
3. import requests
   
4. from lxml import etree
   
5. import os
   
6. 
   
7. 
   
8. def ck_dir():
   
9.     # Please fill in the name of the path where you want to save the images
   
10.     pic_dir = 'mm'
    
11.     if not os.path.exists(pic_dir):
    
12.         os.mkdir(pic_dir)
    
13.     os.chdir(pic_dir)
    
14. 
    
15. 
    
16. def get_pic_url(act_url):
    
17.     r = requests.get(act_url, headers=headers)
    
18.     html = etree.HTML(r.text)
    
19.     # pic list
    
20.     result = html.xpath('//img/@src')
    
21.     # last pic is not mm pic
    
22.     result.pop()
    
23.     # next page url
    
24.     act_nx_pg = html.xpath('//a[contains(text(),"99")]/@href')[0]
    
25.     return result, act_nx_pg
    
26. 
    
27. 
    
28. def main():
    
29.     # pic counter
    
30.     n = 1
    
31.     # check pic directory
    
32.     ck_dir()
    
33.     # pic url list
    
34.     pic_list = []
    
35.     # next page url
    
36.     nx_pg_url = ''
    
37.     # get pics urls
    
38.     for item in range(100, 98, -1):
    
39.         if item == 100:
    
40.             pic_url, nx_pg = get_pic_url(url)
    
41.         else:
    
42.             pic_url, nx_pg = get_pic_url(nx_pg_url)
    
43.         nx_pg_url = f'{url}/{nx_pg}#comments'
    
44.         pic_list.extend(pic_url)
    
45.     # download pics
    
46.     for item in pic_list:
    
47.         r = requests.get('http:' + item, headers=headers)
    
48.         pic_name = item.split('/')[-1]
    
49.         with open(pic_name, 'wb') as f:
    
50.             f.write(r.content)
    
51.             print(f'{pic_name} has been downloaded. total number: {n}')
    
52.             n = n + 1
    
53. 
    
54. 
    
55. if __name__ == '__main__':
    
56.     # global variables
    
57.     url = 'http://jandan.net/ooxx'
    
58.     headers = {'User-agent': 'firefox'}
    
59.     # main func
    
60.     main()
    

复制代码

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

1. import urllib.request
   
2. import os
   
3. import base64
   
4. import re
   
5. 
   
6. 
   
7. def url_open(url):
   
8.     req = urllib.request.Request(url)
   
9.     req.add_header('User-Agent',
   
10.                    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36')
    
11.     response = urllib.request.urlopen(req)
    
12.     html = response.read()
    
13.     #print(html)
    
14. 
    
15.     return html
    
16. 
    
17. 
    
18. def get_page(url):
    
19.     html = url_open(url).decode('utf-8')
    
20. 
    
21.     a = r'<span class="current-comment-page">\[(\d+)\]</span>'
    
22.     page_list = re.findall(a, html)
    
23. 
    
24.     for each in page_list:
    
25.         t = each
    
26. 
    
27.     return t
    
28. 
    
29. 
    
30. def base_num(page_num):
    
31.     times = '20200811-' + str(page_num)
    
32.     s = times.encode('utf-8')
    
33.     sw = base64.b64encode(s)
    
34.     str_sw = str(sw)
    
35.     string = str_sw.split("'")[-1]
    
36.     print(string)
    
37.     return string
    
38. 
    
39. 
    
40. def find_pic_url(url):
    
41.     html = url_open(url).decode('utf-8')
    
42.     pic_url_list = []
    
43. 
    
44.     a = r'<img src="([^"]+\.jpg)"'
    
45.     b = re.findall(a, html)
    
46. 
    
47.     if not len(b):
    
48.         pic_url_list.append(b)
    
49. 
    
50.     for each in pic_url_list:
    
51.         print(each)
    
52. 
    
53. 
    
54. def save_pic(folder, pic_url):
    
55.     pass
    
56. 
    
57. 
    
58. def download_mm(folder='mm', pages=10):
    
59.     # 创建一个文件夹
    
60.     os.mkdir(folder)
    
61.     os.chdir(folder)
    
62. 
    
63.     url = 'http://jandan.net/ooxx/'
    
64.     # 获取页码
    
65.     page_num = int(get_page(url))
    
66. 
    
67.     for i in range(pages):
    
68.         page_num -= i
    
69.         # base64加密
    
70.         x = base_num(page_num)
    
71.         # 获取页码地址
    
72.         page_url = url + x + '#comments'
    
73.         # 获取图片具体地址并保存成列表
    
74.         pic_url = find_pic_url(page_url)
    
75.         save_pic(folder, pic_url)
    
76. 
    
77. 
    
78. if __name__ == '__main__':
    
79.     download_mm()
    

复制代码

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

1. import urllib.request
   
2. import os
   
3. import base64
   
4. import re
   
5. 
   
6. def url_open(url):
   
7.     req = urllib.request.Request(url)
   
8.     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')
   
9.     response = urllib.request.urlopen(req)
   
10.     html = response.read()
    
11.     print(html)
    
12.    
    
13.     return html
    
14. 
    
15.    
    
16. def get_page(url):
    
17.     html = url_open(url).decode('utf-8')
    
18. 
    
19.     a = r'<span class="current-comment-page">\[(\d+)\]</span>'
    
20.     page_list = re.findall(a,html)
    
21. 
    
22.     for each in page_list:
    
23.         t = each
    
24. 
    
25.         return t
    
26. 
    
27.       
    
28. def base_num(page_num):
    
29.     times = '20200811-' + str(page_num)
    
30.     s = times.encode('utf-8')
    
31.     sw = base64.b64encode(s)
    
32.     str_sw = str(sw)
    
33.     string = str_sw.split("'")[-1]
    
34.    
    
35.     return string
    
36. 
    
37. 
    
38. def find_pic_url(url):
    
39.     html = url_open(url).decode('utf-8')
    
40.     pic_url = []
    
41. 
    
42. 
    
43.     a = r'<img src="([^"]+\.jpg)"'
    
44.     b = re.findall(a,html)
    
45.    
    
46.     if not len(b):
    
47.         pic_url.append(b)
    
48. 
    
49.     return pic_url
    
50. 
    
51.         
    
52. def save_pic(folder, pic_url):
    
53.     for each in pic_url:
    
54.         filename = each.split('/')[-1]
    
55.         with open(filename, 'wb') as f:
    
56.             img = open_url(each)
    
57.             f.write(img)
    
58. 
    
59. def download_mm(folder = 'mm', pages = 10):
    
60.     #创建一个文件夹
    
61.     os.mkdir(folder)
    
62.     os.chdir(folder)
    
63. 
    
64.     url = 'http://jandan.net/ooxx/'
    
65.     #获取页码
    
66.     page_num = int(get_page(url))
    
67. 
    
68.     for i in range(pages):
    
69.         page_num -=i
    
70.         #base64加密
    
71.         x = base_num(page_num)
    
72.         #获取页码地址
    
73.         page_url = url + x + '#comments'
    
74.         #获取图片具体地址并保存成列表
    
75.         pic_url = find_pic_url(page_url)
    
76.         save_pic(folder, pic_url)
    
77. 
    
78.         
    
79. if __name__ == '__main__':
    
80.     download_mm()
    

复制代码