[Python爬虫]5.国家地理v3.0

# v3.0进行了代码优化
# 前面两个版本download的是首页的小图片
# 本版本为高清大图

import requests
from bs4 import BeautifulSoup
import re

def getHTMLText(url):    #获取页面
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ''

def getList(list, url):     #拼接出最终图片url和path，并存入数组
    r = getHTMLText(url)
    pic_url = re.findall(r'<a href="/photography/photo_of_the_day/(.*)" title="每日一图：.*">', r)
    for i in range(len(pic_url)):
        page_url = 'http://www.nationalgeographic.com.cn/photography/photo_of_the_day/' + pic_url[i]
        img_url = getPic(page_url)
        r2 = getHTMLText(page_url)
        bsObj = BeautifulSoup(r2, 'html.parser')
        img_name = bsObj.find('div', {'class':'title'}).text[5:]
        img_time = bsObj.find('span', {'class':'time'}).text[10:].replace('.', '')
        img_path = 'E:/pic/' + img_time + img_name + '.jpg'
        list.append([img_url, img_path])



def getPic(p_url):    #通过一级url获取真正的url
    r = getHTMLText(p_url)
    bsObj = BeautifulSoup(r, 'html.parser')
    img_url = bsObj.find('img', {'alt':re.compile('[\u4e00-\u9fa5]')})['src']  #虽然获取到了正确链接，但存疑
    return img_url

def main():
    list = []
    url = 'http://www.nationalgeographic.com.cn/photography/photo_of_the_day/'
    getList(list, url)
    for i in range(len(list)):
        with open(list[i][1], "wb") as f:
            f.write(requests.get(list[i][0]).content)

main()