爬虫初体验

#2017.12.3


#垃圾妹子图
#coding=utf-8
import requests
from bs4 import BeautifulSoup
import os
url = "http://www.enterdesk.com/special/meizi/"   #垃圾妹子图的链接
r = requests.get(url)                             #get到url
r.encoding="utf-8"                                #把编码转化为utf-8国际编码
soup = BeautifulSoup(r.text,'html.parser')        #解析r.text
#data = soup.find('dd',{'class':'egene_spe_pic_li'})#图片在这个标签内，骚操作是不管他，我直接查找'img'标签
grils = soup.find_all('img')                          #这就是骚操作
i =1                                                  #用1，2，3，4来为图片取名
for gril in grils:
    gril_url = gril['src']                           #在错别字girl中查找src
    re = requests.get(gril_url)                      #获取girl的链接
    re.encoding='utf-8'
    with open('girl%d'%i,'wb') as f:                   #文件写入
        f.write(re.content)
        i+=1
        
        
        
#第二个        
#coding=utf-8
import requests
from bs4 import BeautifulSoup
import os

#burl = 'http://www.4j4j.cn/beauty/photos/25196.html'                            #另一个图片网站
for url in range(25190,25196):                                                   #从xxx到xxx页
    gurl = 'http://www.4j4j.cn/beauty/photos/'+str(url)+'.html'                  #用循环来制造其他链接
    r = requests.get(gurl)                                                       #获取资源
    r.encoding='utf-8'
    soup = BeautifulSoup(r.text,'html.parser')
    data = soup.find('div',{'class':'beauty_details_imgs_box'})
    girls = data.find_all('img')
    i = 1
    for girl in girls:
        girl_url = girl['src']
        r = requests.get(girl_url)
        r.encoding = "utf-8"
        with open('girl_%d.jpg'%i,'wb') as f:
            f.write(r.content)
            i+=1