Python 学习记录1

从豆瓣网下载整个相册的图片

从西祠代理网站爬取免费高匿ip 西祠代理

import os,time,requests,random
from bs4 import BeautifulSoup
import urllib
import urllib.request

# Get IP #
def get_proxy(num):
    os.chdir(r'C:\Users\xxxx\Desktop\Python')
    xiciurl = 'http://www.xicidaili.com/nn/{}'
    header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/' '537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'}
    fp = open('host.txt','a+',encoding=('utf-8'))
    for i in range(num+1):
        api = xiciurl.format(i)
        response = requests.get(url=api,headers=header)
        soup = BeautifulSoup(response.text,'lxml')
        container = soup.find_all(name='tr',attrs={'class':'odd'})
        #print(container)
        for tag in container:
            try:
                con_soup = BeautifulSoup(str(tag),'lxml')
                td_list = con_soup.find_all('td')
                #print(td_list)
                ip = str(td_list[1])[4:-5]
                port = str(td_list[2])[4:-5]
                #print(ip,port)
                IPport = ip + '\t' + port + '\n'
                fp.write(IPport)
             except Exception as e:
                print('No IP!')
        time.sleep(1)
    fp.close()  
get_proxy(5) #抓取5页的代理IP地址

验证抓取的IP是否可用

 # verify IP #
def verify_proxy():
    n = 1
    os.chdir(r'C:\Users\xxxx\Desktop\Python')
    url = 'http://www.baidu.com'
    fp = open('host.txt','r')
    ips = fp.readlines()
    proxys = list()
    for p in ips:
        ip = p.strip('\n').split('\t')
        print(ip)
        proxy = 'http:\\' + ip[0] + ip[1]
        proxies = {'proxy':proxy}
        proxys.append(proxies)
    for pro in proxys:
        try:
            s = requests.get(url,proxies=pro)
            print('第{}个ip:{} 状态{}'.format(N,pro,s.status_code))
        except Exception as e:
            print(e)
        n+=1  
verify_proxy()

建立代理IP池

# Build IP pool 
def proxypool(num):
    n = 1
    os.chdir(r'C:\Users\xxxx\Desktop\Python')
    fp = open('host.txt','r')
    proxys = list()
    ips = fp.readlines()
    while n<num:
        for p in ips:
            ip = p.strip('\n').split('\t')
            proxy = 'http:\\' + ip[0] + ip[1]
            proxies = {'proxy':proxy}
            proxys.append(proxies)
            n+=1
    #print(proxys)
    return proxys  

抓取豆瓣相册 再见台湾

def download_album(pages,proxys):
    os.chdir(r'C:\Users\xxxx\Desktop\Python\Douban')
    download_dir = "C:\\Users\\xxxx\\Desktop\\Python\\Douban"
    url = 'https://www.douban.com/photos/album/1634496188/?start='
    headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/' '537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'}
    x = 1
    for i in range(0,pages):
        print(('第{}页').format(i + 1))
        url_cur = url + str(i * 18)
        #print(url_cur)
        try:
            response = requests.get(url_cur, headers=headers, proxies=random.choice(proxys))
            time.sleep(2)
            while response.status_code != 200:
                response = requests.get(url_cur, headers=headers, proxies=random.choice(proxys))
                time.sleep(2)
            soup = BeautifulSoup(respones.text,'lxml')
            imgs = soup.find_all(name='div',attrs={'class':'photo_wrap'})
            #print(imgs)
            y = 0
            for img in imgs:
                imgurls = BeautifulSoup(str(img),'lxml').find_all('img')
                time.sleep(2)
                for u in imgurls:
                    img_url = u.get('src')
                    img_dir = download_dir + '\\'
                    z = str(x) + '_' + str(y)
                    print(('第{}张').format(y+1))
                    #print(img_url)
                    urllib.request.urlretrieve(img_url,'{}{}.jpg'.format(img_dir,z))
                    y = y + 1
                    time.sleep(2)
        except:
            time.sleep(5)
            continue
        x = x + 1
    time.sleep(5)

start = time.time()
proxyPool = proxypool(100)
download_album(17,proxyPool)
end = time.time()
timeUse = int(end-start)
print('耗时{}s'.format(timeUse))