代码如下:
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('/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('/982040.html')
本条技术文章来源于互联网,如果无意侵犯您的权益请点击此处反馈版权投诉
如果觉得《python京东价格_python抓取京东价格分析京东商品价格走势》对你有帮助,请点赞、收藏,并留下你的观点哦!