python项目计划_#python实战计划#1.3练习项目

抓取结果

p{&＃39;lorder_gender&＃39;: &＃39;女&＃39;, &＃39;prices&＃39;: &＃39;438&＃39;, &＃39;lorder_name&＃39;: &＃39;gjy1234&＃39;, &＃39;addr&＃39;: &＃39;上海市徐汇区高安路69弄&＃39;, &＃39;house_image&＃39;: &＃39;http://image.xiaozhustatic1.com/00,800,533/7,0,86,9803,1800,1200,0b2f41ad.jpg&＃39;, &＃39;title&＃39;: &＃39;衡山路 精致一居 近地铁1/7/9/10号线&＃39;}

{&＃39;lorder_gender&＃39;: &＃39;男&＃39;, &＃39;prices&＃39;: &＃39;538&＃39;, &＃39;lorder_name&＃39;: &＃39;王老闆&＃39;, &＃39;addr&＃39;: &＃39;上海市虹口区北苏州路400号河滨大楼&＃39;, &＃39;house_image&＃39;: &＃39;http://image.xiaozhustatic1.com/00,800,533/4,0,68,8498,1798,1200,ca0c88ef.jpg&＃39;, &＃39;title&＃39;: &＃39;看外滩的超大阳台房 沙逊1935的河滨大楼&＃39;}

{&＃39;lorder_gender&＃39;: &＃39;男&＃39;, &＃39;prices&＃39;: &＃39;998&＃39;, &＃39;lorder_name&＃39;: &＃39;风子上海&＃39;, &＃39;addr&＃39;: &＃39;上海市徐汇区余庆路&＃39;, &＃39;house_image&＃39;: &＃39;http://image.xiaozhustatic1.com/00,801,533/6,0,59,6286,1136,756,d7287d22.jpg&＃39;, &＃39;title&＃39;: &＃39;【春上春宿】法租界名人故居/有松鼠飞鸟的院子&＃39;}

……

CODE

from bs4 import BeautifulSoup

import requests

import time

urls &＃61; ["http://sh.xiaozhu.com/search-duanzufang-p{}-0/".format(str(i)) for i in range(1,3)]

def get_detail_url(url):

web_data &＃61; requests.get(url)

time.sleep(1)

soup &＃61; BeautifulSoup(web_data.text, &＃39;lxml&＃39;)

detail_urls &＃61; soup.select(&＃39;#page_list > ul > li >div.result_btm_con.lodgeunitname&＃39;)

for single_detail_url in detail_urls:

data &＃61; single_detail_url.get(&＃39;detailurl&＃39;)

get_page_details(data)#获取每页详细内容

def get_page_details(url, infos &＃61; None):

web_data &＃61; requests.get(url)

time.sleep(1)

soup &＃61; BeautifulSoup(web_data.text, &＃39;lxml&＃39;)

titles &＃61;soup.select(&＃39;body > div.wrap.clearfix.con_bg > div.con_l > div.pho_info > h4 > em &＃39;)

addrs &＃61; soup.select(&＃39;body > div.wrap.clearfix.con_bg > div.con_l > div.pho_info > p > span.pr5 &＃39;)

prices &＃61; soup.select(&＃39;div.day_l > span &＃39;)

house_images &＃61; soup.select(&＃39;#curBigImage&＃39;)

lorder_names &＃61; soup.select(&＃39;#floatRightBox > div.js_box.clearfix > div.w_240 > h6 > a&＃39;)

lorder_genders &＃61; soup.select(&＃39;#floatRightBox > div.js_box.clearfix > div.w_240 > h6 > span &＃39;)

if infos &＃61;&＃61; None:

for title, addr, price, house_image, lorder_name, lorder_gender in zip(titles, addrs, prices, house_images, lorder_names, lorder_genders):

info &＃61; {

&＃39;title&＃39;:title.get_text(),

&＃39;addr&＃39;:addr.get_text().strip(),

&＃39;prices&＃39;:price.get_text(),

&＃39;house_image&＃39;:house_image.get(&＃39;src&＃39;),

&＃39;lorder_name&＃39;:lorder_name.get(&＃39;title&＃39;),

&＃39;lorder_gender&＃39;:get_gender(lorder_gender.get(&＃39;class&＃39;))

}

print(info)

def get_gender(class_name):

if class_name &＃61;&＃61;[&＃39;member_boy_ico&＃39;]:

return &＃39;男&＃39;

elif class_name &＃61;&＃61; [&＃39;member_girl_ico&＃39;]:

return &＃39;女&＃39;

else:

return None

for url in urls:

get_detail_url(url)

心得体会&＃xff1a;

这节课安装lxml库的时候被难住了&＃xff0c;网上到处搜&＃xff0c;最后发现解决办法&＃xff1a;

Paste_Image.png

函数可以嵌套使用&＃xff0c;在本节课的练习中使用了三个函数&＃xff0c;用get_detail_url()函数嵌套get_page_details()。

图片的抓取是难点&＃xff0c;本例中还没有熟练掌握。抓取结果疑似无法下载。