python尝试写简单爬虫

import urllib.request
import re
import time
import random
import os

def getPic():
    url='http://www.wmpic.me/'
    path='E:/picture/'
    rdnum=random.randint(96000,96999)
    url=url+str(rdnum)
    if not os.path.exists(path):
        os.makedirs(path)
    try:
        html=urllib.request.urlopen(url)
        htmls=html.read().decode(encoding='utf-8',errors='strict')
        src=re.findall(' src="(.*?[^0-9].jpg)"',htmls)
        for link in src:
            print(link)
            urllib.request.urlretrieve(link,path+'%s.jpg'%time.time())
    except urllib.error.HTTPError as e:
        print(e.code)
    
getPic()    

-3-23这样爬好像有点乱不是我想要的，现在想想爬下分类的图。那就爬分类的图看看。有了以下代码;

import urllib.request
import re
import time
import os

def getPic():
    url='http://www.wmpic.me/tupian/qingxin/page/'
    urlpg='http://www.wmpic.me/'
    path='E:/qxpicture/'
    url=[url+"{a}".format(a=str(i)) for i in range(1,3)]
    if not os.path.exists(path):
        os.makedirs(path)
    try:
        for ur in url:
            page=urllib.request.urlopen(ur)
            pages=page.read().decode(encoding='utf-8',errors='ignore')
            href=re.findall('<a target="_blank" href="(.*?[0-9])">',pages)
            print(ur)
            for pageur in href:
                html=urllib.request.urlopen(urlpg+pageur)
                htmls=html.read().decode(encoding='utf-8',errors='ignore')
                src=re.findall('<img src="(.*?[^0-9].jpg|.*?[^0-9].png)"',htmls) 
                for link in src:
                    print(link)
                    if link[0:4]=='http':
                        urllib.request.urlretrieve(link,path+'%s.jpg'%time.time())
    except urllib.error.HTTPError as e:
           print(e.code)
      
getPic()  

;

-3-28发现下载的图片混入了其他类图，查看了一下网页，原来右边猜你喜欢的图也抓取下来了，所以想办法过滤。

import urllib.request
import re
import time
import os

def getPic():
    url='http://www.wmpic.me/tupian/qingxin/page/'
    urlpg='http://www.wmpic.me/'
    path='E:/qxpicture/'
    url=[url+"{a}".format(a=str(i)) for i in range(1,3)]
    if not os.path.exists(path):
        os.makedirs(path)
    try:
        for ur in url:
            print(ur)
            page=urllib.request.urlopen(ur)
            pages=page.read().decode()
            href=re.findall('<div id="mainbox">(.*?)<div id="sidebox">',pages,re.S)
            for href1 in href:
                href=href1.replace('\r','').replace('\n','').replace('\t','')
                href=re.findall('<div class="post"><a target="_blank" href="(.*?[0-9])"',href)
                    for pageur in href:
                    html=urllib.request.urlopen(urlpg+pageur)
                    htmls=html.read().decode()
                    src=re.findall('src="(.*?[^0-9].jpg|.*?[^0-9].png)"',htmls)
                    for link in src:
                        print(link)
                        if link[0:4]=='http':
                            urllib.request.urlretrieve(link,path+'%s.jpg'%time.time())
    except urllib.error.HTTPError as e:
           print(e.code)
      
getPic()  

如图；