python爬虫实战及IOError: [Errno ftp error] [Errno 10060]解决方法

最新推荐文章于 2024-05-30 21:56:58 发布

原创

最新推荐文章于 2024-05-30 21:56:58 发布 · 2.8k 阅读

2 ·

CC 4.0 BY-SA版权

同学项目需要大量交通标志，这里就实现一个爬取某交通网站的交通标志图片功能：

import urllib2
import urllib
from bs4 import BeautifulSoup


def get_html(url):#获取到网页的基础html

    request=urllib2.Request(url)
    request.add_header('User-Agent',
                       'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 Edge/16.16299')
    html_content=urllib2.urlopen(request).read()
    return html_content


if __name__=='__main__':
    html = get_html('http://www.jsyks.com/jtbz_1112')#想要爬取的网址
    soup = BeautifulSoup(html, 'html.parser')
    x = 1
    for img in soup.find_all('img'):
        if img.has_attr('src') and img['src'].startswith('//sucimg.itc.cn/sblog/o'):
            image_url = img['src']
            image_url='http:'+image_url
            print(image_url)

            # os.mkdir("pic1")
            # os.chdir("pic1")
            # with open((str(x)+".jpg"),"wb") as f: