Python实战计划学习笔记1.4：爬取http://wehea

代码：

from bs4 import BeautifulSoup
import requests
import time
import urllib.request

path = "C:\\\\Users\\\\album\\\\Desktop\\\\tylor\\\\"
base_url ='http://weheartit.com/inspirations/taylorswift?page'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.106 Safari/537.36'
}

def get_links(num):
    photo_links = []
    for page_num in range(1, num + 1):
        full_url = base_url + str(page_num)
        wb_data = requests.get(full_url)
        soup = BeautifulSoup(wb_data.text, 'lxml')
        time.sleep(2)
        images = soup.select('img.entry-thumbnail')
        for image in images:
            photo_links.append(image.get('src'))

    return photo_links



def dl_image(url):
    urllib.request.urlretrieve(url, path + url.split('/')[-2] + url.split('/')[-1])
    print('Done')


for url in get_links(4):
    dl_image(url)

总结：

用urllib.request.urlretrieve()下载图片