爬取虎扑NBA首页主干道推荐贴的一只小爬虫，日常爬不冷笑话解闷

#-*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
import os, time
import re
url = (r‘https://nba.hupu.com/‘)


#获取不冷笑话在首页的位置，返回url和标题
def get_buleng_title_url(url):
    index_html = requests.get(url)
    index_html_s = BeautifulSoup(index_html.text,‘lxml‘)
    main_street = index_html_s.find(class_ = ‘gray-list main-stem max250‘)
    url_list = []
    url_name_list = []
    for dd in main_street.find_all(‘dd‘,limit = 5):
        url_list.append(dd.a.get(‘href‘))
        url_name_list.append(dd.a.get_text())
    return [url_list[4],url_name_list[4]] 

#获取不冷笑话正文中的图片列表,利用set去重
def get_pic_url(buleng_list):
    pic_url_list = set()
    buleng_html = requests.get(buleng_list[0])
    buleng_html_s = BeautifulSoup(buleng_html.text,‘lxml‘)
    buleng_content = buleng_html_s.find(class_=‘quote-content‘)
    for pic_url in buleng_content.find_all(‘img‘):
        try:
            original_url = pic_url.get(‘data-original‘)
            pic_url_list.add(original_url.split(‘?‘)[0])
        except:
            pic_url_list.add(pic_url.get(‘src‘))
    return pic_url_list

#创建以标题命名的文件夹，并返回是否创建成功
def makedir(buleng_list):
    path = (‘E:\\pic\\%s‘ % buleng_list[1])
    if os.path.exists(path):
        return 0
    else:
        os.makedirs(path)
        return path

#获取亮贴中的图片列表,set去重

def get_comment_pic_url(buleng_list):
    comment_pic_url_list = set()
    buleng_html = requests.get(buleng_list[0])
    buleng_html_s = BeautifulSoup(buleng_html.text,‘lxml‘)
    buleng_comment = buleng_html_s.find(id=‘readfloor‘)
    for floor in buleng_comment.find_all(‘table‘):
        for pic_url in floor.find_all(‘img‘):            
            try:
                original_url = pic_url.get(‘data-original‘)
                comment_pic_url_list.add(original_url.split(‘?‘)[0])
            except:
                comment_pic_url_list.add(pic_url.get(‘src‘))
    return comment_pic_url_list


#下载图片，可下载gif、jpg、png格式
def download_pic(pic_url_list,path,pic_from = ‘正文‘):
    a = 1
    for url in pic_url_list :
        if url.endswith(‘.gif‘):
            pic = requests.get(url)
            with open((path+(‘\\%s-%s.gif‘ % (pic_from,a))),‘wb‘) as f:
                f.write(pic.content)
                f.close
                print(‘下载一张%s动图‘ % pic_from)
            a += 1
        if url.endswith(‘.jpg‘):
            pic = requests.get(url)
            with open((path+(‘\\%s-%s.jpg‘ % (pic_from,a))),‘wb‘) as f:
                f.write(pic.content)
                f.close
                print(‘下载一张%sjpg图‘ % pic_from)
            a +=1
        if url.endswith(‘.png‘):
            pic = requests.get(url)
            with open((path+(‘\\%s-%s.png‘ % (pic_from,a))),‘wb‘) as f:
                f.write(pic.content)
                f.close
                print(‘下载一张%spng图‘ % pic_from)
            a +=1

if __name__ == "__main__":
    buleng = get_buleng_title_url(url)
    path = makedir(buleng)
    if path != 0:
        pic_url_list = get_pic_url(buleng)
        comment_pic_url_list = get_comment_pic_url(buleng)
        download_pic(pic_url_list,path)
        download_pic(comment_pic_url_list,path,‘评论‘)
    else:
        print(‘目录已存在，等待虎扑更新‘)