Python 学习（6）---简单的网页爬虫程序

有些时候我们需要从网上批量下载一些实验数据，编写网页爬虫进行下载可以帮我们节省很多时间，使得办事效率更高，下面是整理的一些基本爬虫程序的代码，其中有些参数得根据计算机浏览器的参数而做适当的调整。

1 批量获取IP地址的爬虫程序：

import urllib.request
import re


def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User Agent', 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36')
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')  #有时会有编码错误，可能跟网页的编码有关

    return html

def getIp(html):
    p = r'(?:(?:[0,1]?\d?\d|2[0-4]\d|25[0-5])\.){3}(?:[0,1]?\d?\d|2[0-4]\d|25[0-5])'
    iplist = re.findall(p, html)

    for each in iplist:
        print(each)


if __name__ == '__main__':
    url = 'http://www.youdaili.net/Daili/guonei/3661.html'
    #url = 'http://cn-proxy.com'
    getIp(url_open(url))

2 批量下载妹子图：

import urllib.request
import os

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.130 Safari/537.36')
    response = urllib.request.urlopen(req)  # 修改header，避开浏览器的检查
    html = response.read()

    return html

def get_page(url):
    html = url_open(url).decode('utf-8')

    a = html.find('current-comment-page') + 23  # 需要加一个偏移量
    b = html.find(']', a)

    return html[a:b]
    
    
def find_imgs(url):
    html = url_open(url).decode('utf-8')
    img_addrs = []

    a = html.find('img src=')
    

    while a != -1:
        b = html.find('.jpg', a, a+255)
        if b != -1:
            img_addrs.append(html[a+9:b+4])      # 需要加一个偏移量
        else:
            b = a + 9

        a = html.find('img src=', b)

    for i in range(3):   # 删除后面几个错误的地址
        img_addrs.pop()
        

    return img_addrs

def save_imgs(folder, img_addrs):
    for each in img_addrs:
        filename = each.split('/')[-1]
        print(filename)
        with open(filename,'wb') as f:
            img = url_open(each)
            f.write(img)
   
def download_mm(folder='OOXX1', pages=5):
    os.mkdir(folder)
    os.chdir(folder)

    url = "http://jandan.net/ooxx/"
    page_num = int(get_page(url))
    
    for i in range(pages):
        page_num -= i
        page_url = url + 'page-' + str(page_num) + '#comments'
        img_addrs = find_imgs(page_url)
        save_imgs(folder, img_addrs)

if __name__ == '__main__':
    download_mm()

3 利用正则表达式下载妹子图：

import urllib.request
import os
import re

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.130 Safari/537.36')
    response = urllib.request.urlopen(req)  # 修改header，避开浏览器的检查
    html = response.read().decode('utf-8')

    return html


def get_imgs(html):
    #p = r'bpic="([^"]+\.jpg)"'           # 大图
    p = r'data-original="([^"]+\.jpg)"'   # 小图
    imglist = re.findall(p,html)

    '''
    for each in imglist:
        print(each)
    
    '''
    folder = "mm1"   # 建一个文件夹存储图片
    os.mkdir(folder)
    os.chdir(folder)
    
    for each in imglist:
        filename = each.split('/')[-1]
        print(filename)
        urllib.request.urlretrieve(each, filename, None)   # 检索图片并下载到当前目录
    
        

if __name__ == '__main__':
#   url = "http://tieba.baidu.com/f?kw=%E5%A6%B9%E5%AD%90%E5%9B%BE&ie=utf-8"
    url = "http://tieba.baidu.com/f?kw=%E5%A6%B9%E5%AD%90%E5%9B%BE&fr=search"
    get_imgs(url_open(url))