代碼如下:

fromcreepyimportCrawler

fromBeautifulSoupimportBeautifulSoup

importurllib2

importjson

classMyCrawler(Crawler):

defprocess_document(self,doc):

ifdoc.status==200:

print‘[%d]%s’%(doc.status,doc.url)

try:

soup=BeautifulSoup(doc.text.decode(‘gb18030’).encode(‘utf-8’))

exceptExceptionase:

printe

soup=BeautifulSoup(doc.text)

printsoup.find(id=”product-intro”).div.h1.text

url_id=urllib2.unquote(doc.url).decode(‘utf8’).split(‘/’)[-1].split(‘.’)[0]

f=urllib2.urlopen(‘?skuid=J_’+url_id,timeout=5)

price=json.loads(f.read())

f.close()

printprice[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(‘’)

轉(zhuǎn)載請注明：seo-網(wǎng)站優(yōu)化-網(wǎng)站建設?python抓取京東價格分析京東商品價格走勢