python爬虫：案例二:携程网酒店价格信息

这个案例可能不太智能，有个朋友和我说他们公司让他爬携程的酒店价格信息，我当时去看了一下，发现携程的信息爬起来挺麻烦，城市是必输项，酒店名是选输项，跳转的url中城市后面带一个数字，对于这个每个城市表示的数字的规则我不知道，这样我只能定向爬一个城市，或者就是模拟浏览器之类，觉得挺麻烦，到了酒店页面又有挺多东西看着头疼，我对他说这个挺麻烦的，分析花的时间会很久，后来他说他们公司是人工输入酒店价格详情的url到数据库，然后直接从一个页面获取价格数据

#coding=utf-8
import sys
reload(sys)
sys.setdefaultencoding( "utf-8" )
import urllib
from selenium import webdriver

urls=['http://hotels.ctrip.com/hotel/848702.html#ctm_ref=hod_sr_lst_dl_n_2_1']
＃假设一堆url
class Xc():
    def pc(seif):
        for url in urls:
            driver = webdriver.PhantomJS() 
            driver.get(url)
            fangx_1=driver.find_element_by_class_name('room_unfold').text.split('\n')[0]
            jiage_1=driver.find_element_by_class_name('base_price').text
            driver.quit
            return fangx_1+'|'+jiage_1
            ＃房型和对应的价格

s=Xc()
print s.pc()

结果：

单人房（无窗）｜¥237

上面的代码只是简单的例子，而且所有房型价额需要一个一个解析，太麻烦了，后来我发现源码最下面居然有一段json，里面的内容就是房型，价格这些，于是我改了一下代码

#coding=utf-8
import sys
reload(sys)
sys.setdefaultencoding( "utf-8" )
import urllib
from selenium import webdriver

urls=['http://hotels.ctrip.com/hotel/848702.html#ctm_ref=hod_sr_lst_dl_n_2_1']

class Xc():
    def pc(seif):
        for url in urls:
            driver = webdriver.PhantomJS() 
            driver.get(url)
            #fangx_1=driver.find_element_by_class_name('room_unfold').text.split('\n')[0]
            #jiage_1=driver.find_element_by_class_name('base_price').text
            json=driver.find_element_by_xpath('//*[@id="htl_detail_htl_hotel"]').get_attribute('value')
            driver.quit
            #return fangx_1+'|'+jiage_1
            return json

s=Xc()
print s.pc()

结果：

pageid=102003;ht=848702;checkin=2016-05-09;checkout=2016-05-10;rmlist=[{"rm":"30665921","shadowid":"0","rpfq":"0.0","rpfh":"219","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"大床","breakfast":"0","policy":"免费取消","guaranteetype":"F","bk":"T","isgift":"F","isgroup":"F"},{"rm":"30265080","shadowid":"0","rpfq":"0.0","rpfh":"263","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"大床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"T","isgift":"F","isgroup":"F"},{"rm":"24125027","shadowid":"0","rpfq":"0.0","rpfh":"294","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"大床","breakfast":"0","policy":"免费取消","guaranteetype":"F","bk":"T","isgift":"F","isgroup":"F"},{"rm":"8684722","shadowid":"0","rpfq":"0.0","rpfh":"294","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"大床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"F","isgift":"F","isgroup":"F"},{"rm":"30265081","shadowid":"0","rpfq":"0.0","rpfh":"219","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"双床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"T","isgift":"F","isgroup":"F"},{"rm":"8684723","shadowid":"0","rpfq":"0.0","rpfh":"294","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"双床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"F","isgift":"F","isgroup":"F"},{"rm":"30265075","shadowid":"0","rpfq":"0.0","rpfh":"237","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"单人床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"T","isgift":"F","isgroup":"F"},{"rm":"24125024","shadowid":"0","rpfq":"0.0","rpfh":"265","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"单人床","breakfast":"0","policy":"免费取消","guaranteetype":"F","bk":"T","isgift":"F","isgroup":"F"},{"rm":"2890470","shadowid":"0","rpfq":"0.0","rpfh":"265","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"单人床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"F","isgift":"F","isgroup":"F"},{"rm":"30265074","shadowid":"0","rpfq":"0.0","rpfh":"254","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"大床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"T","isgift":"F","isgroup":"F"},{"rm":"24125041","shadowid":"0","rpfq":"0.0","rpfh":"284","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"大床","breakfast":"0","policy":"免费取消","guaranteetype":"F","bk":"T","isgift":"F","isgroup":"F"},{"rm":"2890480","shadowid":"0","rpfq":"0.0","rpfh":"284","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"大床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"F","isgift":"F","isgroup":"F"},{"rm":"30265072","shadowid":"0","rpfq":"0.0","rpfh":"280","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"双床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"T","isgift":"F","isgroup":"F"},{"rm":"24125016","shadowid":"0","rpfq":"0.0","rpfh":"313","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"双床","breakfast":"0","policy":"免费取消","guaranteetype":"F","bk":"T","isgift":"F","isgroup":"F"},{"rm":"2525661","shadowid":"0","rpfq":"0.0","rpfh":"313","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"双床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"F","isgift":"F","isgroup":"F"},{"rm":"30265079","shadowid":"0","rpfq":"0.0","rpfh":"305","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"大床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"T","isgift":"F","isgroup":"F"},{"rm":"2525665","shadowid":"0","rpfq":"0.0","rpfh":"341","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"大床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"F","isgift":"F","isgroup":"F"},{"rm":"30265077","shadowid":"0","rpfq":"0.0","rpfh":"305","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"双床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"T","isgift":"F","isgroup":"F"},{"rm":"24125021","shadowid":"0","rpfq":"0.0","rpfh":"341","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"双床","breakfast":"0","policy":"免费取消","guaranteetype":"F","bk":"T","isgift":"F","isgroup":"F"},{"rm":"8684720","shadowid":"0","rpfq":"0.0","rpfh":"341","pt":"FG","mt":"0.0","pn":"0.0","promotiontype":"0","iscomfirm":"F","bedtype":"双床","breakfast":"0","policy":"不可取消","guaranteetype":"T","bk":"T","isgift":"F","isgroup":"F"}]

rpfh是价格

bedtype是房型