第一周第四课时

运行结果 运行图片

from bs4 import BeautifulSoup
import requests
import urllib.request
data1 = []
data2 = []
path = 'C:/Users/zhangyang/Desktop/swift/'


def get_url(url):
    web_data = requests.get(url)
    soup = BeautifulSoup(web_data.text, 'lxml')
    headerimgs = soup.select('#main-container > div > div.header > div.header-cover')
    contentimgs = soup.select('img')
    # for headerimg in headerimgs:
    #     #data1.append(headerimg.get('style'))
    #     data1 =data1[0][23:-2]
    #     print(data1)
    for contentimg in contentimgs:
        data2.append(contentimg.get('src'))
        print(data2)


def get_pic(start, end):
    for i in range(start, end):
        get_url('http://weheartit.com/inspirations/taylorswift?page='+str(i))
    # for url in data1:
    #     urllib.request.urlretrieve(url, path + url.split('/')[-2] + url.split('/')[-1])
    #     print('done')
    for url in data2:
        urllib.request.urlretrieve(url, path + url[-10:])
        print('done')
get_pic(0, 1)