Python学习之爬虫

Posted 2020-12-16 无法手执玫瑰

又被老师要求去搞Python ,曰,,下午回顾了一下Python的基础知识,写了个爬取图片的程序,在此做个分享吧。不喜勿喷

import requests
import time
from bs4 import BeautifulSoup
import uuid

# 下载单个页面的一些图片
def downLoader(url,page):
    headers = {‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.104 Safari/537.36 Core/1.53.4843.400 QQBrowser/9.7.13021.400‘}
    if(page == 1):
        res = requests.get(url + "index.html", headers=headers)  # 第一页
    if(page != 1):
        page = str(page)
        res = requests.get(url + "index_" + page + ".html", headers=headers)

    res.encoding = ‘gbk‘
    soup = BeautifulSoup(res.text, ‘lxml‘)
    for i in range(1,22):
        i = str(i)
        if page == 1:
            add = soup.select(‘#main > div.slist > ul > li:nth-child(‘ + i + ‘) > a > span > img‘)
        else:
            add = soup.select(‘#main > div.slist > ul > li:nth-child(‘ + i + ‘) > a > img‘)

        #在下面写下载到本地的代码
        # print(url + add[0].get(‘src‘))
        down(url + add[0].get(‘src‘), str(uuid.uuid1()))
    #for index in add:
        #print(url + add[index].get(‘src‘))
        # return url + add[index].get(‘src‘)  # 返回url
    pass

def down(url, name):
    with open(‘G:学习PyCharmPyCharm2017py工作环境爬虫壁纸‘+ name+‘.png‘, ‘wb+‘) as f:
        f.write(requests.get(url).content)
        f.flush()
    pass
if __name__ == ‘__main__‘:
    url = ‘http://pic.netbian.com/‘
    print(‘请骚等````‘)
    for i in range(1,11):
        time.sleep(0.5)
        downLoader(url,i)