python简单爬虫编写

Posted 2020-06-11

 1.主要学习这程序的编写思路

a.读取解释网站

b.找到相关页

c.找到图片链接的元素

d.保存图片到文件夹

.....

将每一个步骤都分解出来,然后用函数去实现,代码易读性高.

##代码尽快运行时会报错,还须修改

 

import urllib.request
import os

def url_open(url):    #读取解释
    req = urllib.request.Request(url)
 #   req.add_header(\‘User-Agent\‘,\‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/36.0.1985.125 Safari/537.36\‘)
    response = urllib.request.urlopen(req)
    html = response.read()

    return html

def get_page(url):   #找到相关页
    html = url_open(url)

    a = html.find(‘current-comment-page‘)
    b = html.find(a)

    return html[a:b]


def find_imgs(url):  #找到图片链接的元素
    html = url_open(url)
    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])
        else:
            b = a +9

        a = html.find(‘img src=‘,b‘)

    return img_addrs

def save_imgs(folder, img_addrs):   #保存图片到文件夹
    for each in img_addrs:
        filename = each.split(‘\‘/\‘‘)
        with open(filename,‘wb‘) as f:
            img =url_open(each)
            f.write(img)


def download_mm(folder=‘OOXX‘,pages=10):
    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(img_addrs)

if __name__ == ‘__main__‘:
    download_mm()