閒著沒事嘗試抓一下京東的資料,需要使用到的庫有:BeautifulSoup,urllib2,在Python2下測試透過
from creepy import Crawler from BeautifulSoup import BeautifulSoup import urllib2 import json class MyCrawler(Crawler): def process_document(self, doc): if doc.status == 200: print '[%d] %s' % (doc.status, doc.url) try: soup = BeautifulSoup(doc.text.decode('gb18030').encode('utf-8')) except Exception as e: print e soup = BeautifulSoup(doc.text) print soup.find(id="product-intro").div.h1.text url_id=urllib2.unquote(doc.url).decode('utf8').split('/')[-1].split('.')[0] f = urllib2.urlopen('http://p.3.cn/prices/get?skuid=J_'+url_id,timeout=5) price=json.loads(f.read()) f.close() print price[0]['p'] else: pass crawler = MyCrawler() crawler.set_follow_mode(Crawler.F_SAME_HOST) crawler.set_concurrency_level(16) crawler.add_url_filter('\.(jpg|jpeg|gif|png|js|css|swf)$') crawler.crawl('http://item.jd.com/982040.html')
部分執行結果:
[200] http://item.jd.com/519836.html
三星 HM1200 原裝藍芽耳機 黑色
118.00
[200] http://item.jd.com/603133.html
捷波朗 EASYVOICE+ 易音 藍芽耳機 黑色
-1
[200] http://item.jd.com/1030552473.html
【年終熱賣】嘉源手機N699 2.8寸雙屏雙卡雙待雙電2000毫安翻蓋手機 黑
268.00