爬虫入门1——爬图

低级版

import urllib.request
import os

def url_open(url):
    req=urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36')
    response=urllib.request.urlopen(url)  
    html=response.read()
    return html

def get_page(url):

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

    a=html.find('current-comment-page')+23
    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(('http:'+html[a+9:b+4]))
        else:

            b=a+9

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

def save_imgs(img_addrs):
    for each in img_addrs:
        filename=each.split('/')[-1]
        with open(filename,'wb') as f:
            img=url_open(each)
            f.write(img)


def download_mm(folder='picture',pages=10):

    if not os.path.exists(folder):
        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'
        print(page_url)
        img_addrs=find_imgs(page_url)
        save_imgs(img_addrs)

if __name__=='__main__':
    download_mm()

正则化版

import urllib.request
import os
import re
def url_open(url):
    req=urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36')
    response=urllib.request.urlopen(url)  
    html=response.read()
    return html

def get_page(url):

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

    a=html.find('current-comment-page')+23
    b=html.find(']',a)
    return html[a:b]



def get_imgs(url):
    html=url_open(url).decode('utf-8')
    p=r'src="(.+\.jpg)"'
    imglist=re.findall(p,html)

    for each in imglist:
        filename=each.split('/')[-1]
        urllib.request.urlretrieve('http:'+each,filename)

def download_mm(folder='picture',pages=10):

    if not os.path.exists(folder):
        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'
        print(page_url)
        get_imgs(page_url)


if __name__=='__main__':
    download_mm()