多线程爬妹子图

发表于 | 更新于: | 分类于 | 阅读次数: |
字数统计: 702 字 | 阅读时长 ≈ 3 分钟

原来的代码有点问题，改了以后成功添加多线程，都跑一分钟，多线程要多爬120张图片，这样看来效率果然高了许多。
先上普通的:

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
import requests
import os
import re
import random


dirs="D:/妹子图"
headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.4094.1 Safari/537.36'}
def mkdir():
	if not os.path.exists(dirs):
		os.mkdir('D:/妹子图')
		os.chdir('D:/妹子图')
		return True
	else:
		print("妹子图文件夹已存在")
		return False

def get_max_page():
	url="https://www.mzitu.com/zipai/"
	r = requests.get(url,headers=headers)
	result=re.findall("<span aria-current='page' class='page-numbers current'>(.*?)</span>",r.text,re.S)
	return result[0]


def find_onepage_imgs(url):
        r=requests.get(url,headers=headers)
        result=re.findall('<div class="comment-meta commentmetadata"><a href=".*?">(.*?)</a>.*?</div>.*?<p><img class="lazy".*?data-original="(.*?)".*?</p>',r.text,re.S)
        #print(result[0][0].split())
        return result
def download_img(img,path,i):
    with open(path+str(int(random.random()*100)) + ".jpg", 'wb+') as f:
        print("下载第" + str(i) + "页提交于" + path + "的图片")
        f.write(img.content)


if __name__== '__main__':
        mkdir()
        print (os.getcwd())
        
        max_page=get_max_page()
        for i in range(int(max_page),1,-1):
                onepage_list=find_onepage_imgs("http://www.mzitu.com/zipai/comment-page-"+ str(i)+"/#comments" )
                for j in onepage_list:
                        path=j[0].split()   
                        path=path[0][0:4]+path[0][5:7]+path[0][8:10]+path[1]+path[2][0:2]+path[2][3:5]  
                        img=requests.get(j[1])
                        download_img(img,path,i)

必须要说的是，之前下载图片名称是网站上的提交时间，然后提交时间会有相同，所以我判断如果文件名相同则文件名加排序。现在我直接在文件名后加一个随机数,就不用那么麻烦了。下面是多线程爬虫:

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
import requests
import os
import re
import random
import threading
dirs = "D:/妹子图"
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.4094.1 Safari/537.36'}


def mkdir():
    if not os.path.exists(dirs):
        os.mkdir('D:/妹子图')
        os.chdir('D:/妹子图')
        return True
    else:
        print("妹子图文件夹已存在")
        return False


def get_max_page():
    url = "https://www.mzitu.com/zipai/"
    r = requests.get(url, headers=headers)
    result = re.findall("<span aria-current='page' class='page-numbers current'>(.*?)</span>", r.text, re.S)
    return result[0]


def find_onepage_imgs(url):
    r = requests.get(url, headers=headers)
    result = re.findall(
        '<div class="comment-meta commentmetadata"><a href=".*?">(.*?)</a>.*?</div>.*?<p><img class="lazy".*?data-original="(.*?)".*?</p>',
        r.text, re.S)
    # print(result[0][0].split())
    return result
def download_img(img,path,i):
    with open(path+str(int(random.random()*100)) + ".jpg", 'wb+') as f:
        print("下载第" + str(i) + "页提交于" + path + "的图片")
        f.write(img.content)


if __name__ == '__main__':
    mkdir()
    print(os.getcwd())

    max_page = get_max_page()
    for i in range(int(max_page), 1, -1):
        onepage_list = find_onepage_imgs("http://www.mzitu.com/zipai/comment-page-" + str(i) + "/#comments")
        threads=[]
        for j in onepage_list:
            path = j[0].split()
            path = path[0][0:4] + path[0][5:7] + path[0][8:10] + path[1] + path[2][0:2] + path[2][3:5]
            img = requests.get(j[1])
            t=threading.Thread(target=download_img,args=(img,path,i))
            threads.append(t)
        for i in range(0, len(threads) - 1):
            threads[i].start()
        for i in range(0, len(threads) - 1):
            threads[i].join()