爬取圖片並存入資料夾中
阿新 • • 發佈:2019-01-29
import urllib.request import urllib.parse import re
def handler_url(page,base_url):
url = base_url + str(page) + '/' headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36' } request = urllib.request.Request(url=url,headers=headers) response = urllib.request.urlopen(request) return response.read().decode('utf-8') def search_img(html): pattern = re.compile(r'<div class="thumb">.*?<img src="(.*?)" alt=.*?/>.*?</div>',re.S) img_list = pattern.findall(html) return img_list
def download(img_url): img_url = 'https:' + img_url filename = img_url.split('/')[-1] filename = './tupian/' + filename urllib.request.urlretrieve(img_url,filename=filename) def main(): base_url = 'https://www.qiushibaike.com/pic/page/' start_page= int(input('輸入起始頁:')) end_page = int(input('輸入結束頁:')) for page in range(start_page,end_page+1): html=handler_url(page,base_url) # 處理url img_list = search_img(html) # 正則搜尋 print(img_list) for img_url in img_list: download(img_url) if __name__ == '__main__': main()