python-单线程图片爬取

0x01代码

from bs4 import BeautifulSoup
import requests
import time
import re
from multiprocessing import Process

headers = {
    'user-agent':'Mozilla/5.0 (Windows NT 6.1; W…) Gecko/20100101 Firefox/61.0'
}

def get_url(url):
    res = requests.get(url)
    if res.status_code == 200:
        # soup = BeautifulSoup(res.text,'html.parser')
        # re = soup.find('div',class_='container').find_all('li')
        # for i in re:
        #     s = i.find('img').get('src')
        #     print(s)
        #     li.append(s)
        html_text = res.text;
        img_list = re.findall('<img class="lazy" src="(.*?)"',html_text)
    return img_list

def get_img_url(url):
    #url = "//img2.woyaogexing.com/2021/03/31/8abad21b96f74d7d8bdde4382245dca3!360x640.jpeg"
    url_s = url.split("!")
    url_url =""
    if len(url_s) == 2:
        url_s1 = url_s[0]
        if "." in url_s[1]:
            url_s2 = url_s[1].split(".")[-1]
            url_url = "https:" + url_s1 + "." + url_s2
    return url_url;

def get_img(url):
    # s = url.split('/')[-1].split('_')[0]
    # print(s)
    # url = "https:"+url
    # print(url)
    url = get_img_url(url)
    print(url)
    if "woyaogexing.com" not in url:
        return
    r = requests.get(url)
    if r.status_code == 200:
        img_path = "mingxing/"+url.split('/')[-1]
        with open(img_path,'wb') as f:
            f.write(r.content)

if __name__ == '__main__':
    #url = 'https://www.woyaogexing.com/shouji/mingxing/'
    for i in range(2,100):
        url = "https://www.woyaogexing.com/tupian/dongman/index_"+str(i)+".html"
        img_url = get_url(url)
        start = time.time()
        p_l = []
        for i in img_url:
            get_img(i)
            # p = Process(target=get_img,args=(i,))
            # p.start()
            # p_l.append(p)

        #[i.join() for i in p_l]
    print(time.time() - start)

0x02待优化

等待优化为多线程的爬取方式

原文链接: python-单线程图片爬取 版权所有,转载时请注明出处,违者必究。
注明出处格式:流沙团 ( https://www.gyarmy.com/post-641.html )

发表评论

0则评论给“python-单线程图片爬取”