import requests
from bs4 import BeautifulSoup
import time
def get_image_href(url):
html=requests.get(url)
bshtml=BeautifulSoup(html.text,'lxml')
# 獲取照片鏈接
image_hrefs=bshtml.select('div.grid-thumb.grid-responsive > div > div > div > a > img')
hrefs=[]
for href in image_hrefs:
hrefs.append(href.get('src'))
time.sleep(2)
print("Get One")
return hrefs
get_image_href('http://weheartit.com/inspirations/taylorswift?page=4')
week1_4.py
from GetImagePage import get_image_href
from GetImage import get_image
def main():
urls=["http://weheartit.com/inspirations/taylorswift?page={}".format(str(i)) for i in range(1,21)]
for url in urls:
part_url=get_image_href(url)
for imageUrl in part_url:
get_image(imageUrl)
main()
