爬蟲基礎練習—python爬蟲下載豆瓣妹子圖片

下載指定網站上的妹子圖片，這裏只抓了前100頁的圖片，可根據須要本身設置頁數
cat值爲圖片類型，你們能夠自行更改cat值體驗一下，有問題留言給我，看到就會解答
2 ＝ 大胸妹
3 ＝ 美腿控
4 ＝ 有顏值
5 ＝ 大雜燴
6 ＝ 小翹臀

import requests
import re
import time
from bs4 import BeautifulSoup

cat ='2'
img = 'http://www.dbmeinv.com/dbgroup/show.htm?cid='+ cat
end = '/dbgroup/show.htm?cid='+ cat + '&pager_offset=100'
urls = [ ]
def getURLs(mainURL):
    time.sleep(1)
    headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.80 Safari/537.36'}
    html = requests.get(mainURL).text
    soup = BeautifulSoup(html, 'html.parser')
    picURL = re.findall('<img class.*?src="(.+?\.jpg)"', html, re.S)
    for url in picURL:
        urls.append(url)
        print(url)
    asoup = soup.select('.next a')[0]['href']
    Next_page = 'http://www.dbmeinv.com' + asoup
    if asoup != end:
        getURLs(Next_page)
    else:
        print('連接已處理完畢！')
    return urls
url = getURLs(img)

i = 0
for each in url:
    pic = requests.get(each, timeout = 10)
    picName = 'pictures/' + str(i) + '.jpg'
    fp = open(picName, 'wb')
    fp.write(pic.content)
    fp.close()
    i += 1

print('圖片下載完成')