Python爬取 鬥圖表情,讓你成為鬥圖大佬
阿新 • • 發佈:2019-01-04
話不多說,上結果(只爬了10頁內容)
上程式碼:(可直接執行) 用到Xpath
#encoding:utf-8 # __author__ = 'donghao' # __time__ = 2018/12/24 15:20 import requests import urllib.request import urllib3 import os import re import time from lxml import etree def parse_page(url): headers = { 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:57.0) Gecko/20100101 Firefox/57.0' } resp = requests.get(url=url,headers=headers) text = resp.text html = etree.HTML(text) imgs = html.xpath("//div[@class='page-content text-center']//img[@class!='gif']") for img in imgs: #獲取圖片url img_url = img.get('data-original') #獲取圖片Url的字尾名 end = os.path.splitext(img_url)[1] #替換掉url中特殊字元 end = re.sub(r'[,。??,/\\·]','',end) # 獲取圖片描述,並加上字尾 name = img.get('alt')+end #檔名為 #下載到本地資料夾 urllib.request.urlretrieve(img_url,'images/'+name) def main(): #爬取10頁 for x in range(1,10): url = 'http://www.doutula.com/photo/list/?page=%d'%x parse_page(url) if __name__ == '__main__': start = time.time() main() end = time.time() print('耗時:%0.002fs' % (end - start))