需要爬取的资料
网址： http://bj.xiaozhu.com/
爬取信息：
爬取网页上300个房源信息，包括标题，地址，日租金，第一张房源图片链接，房东图片链接，房东性别，房东名字
代码
from bs4 import BeautifulSoup
import requests
# 判断性别
def get_sex(sex_icon):
if sex_icon == ['member_ico']:
return "男"
if sex_icon == ['member_ico1']:
return "女"
else:
return "未标识"
# 获取每页的url链接
def get_page_url(url):
web_url = requests.get(url)
web_url_soup = BeautifulSoup(web_url.text,'lxml')
page_urls = web_url_soup.select('#page_list > ul > li > a')
for page_url in page_urls:
each_url = page_url.get('href')
get_detail_info(each_url)
def get_detail_info(url):
web_data = requests.get(url)
soup = BeautifulSoup(web_data.text,'lxml')
titles = soup.select('body > div.wrap.clearfix.con_bg > div.con_l > div.pho_info > h4 > em')
addresses = soup.select('body > div.wrap.clearfix.con_bg > div.con_l > div.pho_info > p > span.pr5')
prices = soup.select('#pricePart > div.day_l > span')
pics1 = soup.select('#curBigImage')
owner_pics = soup.select('#floatRightBox > div.js_box.clearfix > div.member_pic > a > img')
owner_names = soup.select('#floatRightBox > div.js_box.clearfix > div.w_240 > h6 > a')
sexes = soup.select('#floatRightBox > div.js_box.clearfix > div.member_pic > div')
for title, address, price, pic1, owner_name, owner_pic, sex in zip(titles, addresses, prices, pics1, owner_names,
owner_pics, sexes):
data = {
'title': title.get_text(),
'address': address.get_text(),
'price': price.get_text(),
'pic': pic1.get('src'),
'owner_pic': owner_pic.get('src'),
'name': owner_name.get('title'),
'sex': get_sex(sex.get('class'))
}
print (data)
urls = ["http://bj.xiaozhu.com/search-duanzufang-p{}-0/".format(number) for number in range(1, 10)]
for url in urls:
get_page_url(url)成果
{'name': '想要', 'address': '北京市朝阳区望京利泽西园\n ', 'price': '395', 'owner_pic': 'http://image.xiaozhustatic1.com/21/5,0,44,1477,329,329,ea609ac8.jpg', 'title': '望京华彩十四号线精美豪华大一居', 'sex': '未标识', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/6,0,39,2965,1800,1200,f17d1a3e.jpg'}
{'name': '暖阳洋Sunny', 'address': '北京市朝阳区彩虹路\n ', 'price': '798', 'owner_pic': 'http://image.xiaozhustatic1.com/21/2,0,86,206,375,375,d46c51ef.jpg', 'title': '紧邻798、望京、酒仙桥，精品大三居。', 'sex': '未标识', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/3,0,34,2819,1800,1200,e051c333.jpg'}
{'name': '小小西红柿', 'address': '北京市丰台区六里桥太平桥西里40号\n ', 'price': '368', 'owner_pic': 'http://image.xiaozhustatic1.com/21/6,0,72,1777,260,260,887558a2.jpg', 'title': '临近 北京西站 距电力医院3分钟 两居', 'sex': '女', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/6,0,28,4451,1800,1200,e3bb1749.jpg'}
{'name': '想要', 'address': '北京市朝阳区广顺北大街利泽西园\n ', 'price': '395', 'owner_pic': 'http://image.xiaozhustatic1.com/21/5,0,44,1477,329,329,ea609ac8.jpg', 'title': '望京商圈，毗邻地铁5分钟，漫威主题大两居', 'sex': '未标识', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/6,0,66,803,1800,1200,38a4c686.jpg'}
{'name': '最美好的时光遇到你', 'address': '北京市朝阳区小关北里\n ', 'price': '218', 'owner_pic': 'http://image.xiaozhustatic1.com/21/4,0,84,10730,260,260,6d756363.jpg', 'title': '惠新西街南口阳光大主卧', 'sex': '女', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/5,0,47,2122,1800,1200,8830e613.jpg'}
{'name': '暖阳洋Sunny', 'address': '北京市朝阳区彩虹路\n ', 'price': '268', 'owner_pic': 'http://image.xiaozhustatic1.com/21/2,0,86,206,375,375,d46c51ef.jpg', 'title': '独立卫浴邻798、望京、酒仙桥更多优惠房源。', 'sex': '未标识', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/2,0,71,458,1800,1200,a9c5ea82.jpg'}
{'name': '阳光艳艳', 'address': '北京市朝阳区苹果社区北区\n ', 'price': '398', 'owner_pic': 'http://image.xiaozhustatic1.com/21/5,0,59,2841,363,363,8b6cf3d7.jpg', 'title': '国贸双井10号线苹果酒店式公寓', 'sex': '女', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/6,0,25,3184,1800,1200,4b993d38.jpg'}
{'name': '兰花姐', 'address': '北京市朝阳区十里河左安东路弘善家园\n ', 'price': '279', 'owner_pic': 'http://image.xiaozhustatic1.com/21/4,0,2,9806,329,329,4656b7f6.jpg', 'title': '潘家园十里河地铁十号十四号临近国贸', 'sex': '女', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/6,0,83,2043,1800,1200,cc659348.jpg'}
{'name': 'Alicejy', 'address': '北京市朝阳区望京南湖中园\n ', 'price': '195', 'owner_pic': 'http://image.xiaozhustatic1.com/21/6,0,3,3065,160,160,ba886bf8.jpg', 'title': '望京亲水微豪庭，独享奢华对望东湖湾', 'sex': '女', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/6,0,62,3156,1800,1200,7d5aa8bc.jpg'}
{'name': '小肖肖', 'address': '北京市东城区南锣鼓巷\n ', 'price': '158', 'owner_pic': 'http://image.xiaozhustatic1.com/21/5,0,55,1517,260,260,ea96ce11.jpg', 'title': '南锣鼓巷0距离，鼓楼、后海、故宫、簋街', 'sex': '女', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/1,0,53,2309,825,550,5a3a9a34.jpg'}
{'name': '豹子楠', 'address': '北京市西城区高粱桥斜街长河湾\n ', 'price': '398', 'owner_pic': 'http://image.xiaozhustatic1.com/21/1,0,8,5386,333,333,764cfdb4.jpg', 'title': '西直门 长河湾 韩式田园温馨2居', 'sex': '女', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/1,0,3,5482,825,550,f874984d.jpg'}
{'name': '幸福姐姐', 'address': '北京市朝阳区红军营南路\n ', 'price': '128', 'owner_pic': 'http://image.xiaozhustatic1.com/21/1,0,93,4699,375,375,f8bc8f9b.jpg', 'title': '北五环5.13号地铁高档的温馨公寓', 'sex': '女', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/1,0,42,4845,825,550,57c0343f.jpg'}
{'name': 'Rolling_meng', 'address': '北京市朝阳区劲松华腾园\n ', 'price': '318', 'owner_pic': 'http://image.xiaozhustatic1.com/21/5,0,96,1555,375,375,ea000c2a.jpg', 'title': '10号线劲松/双井/国贸CBD采光舒适大一居', 'sex': '男', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/6,0,40,333,1800,1200,c8e516a7.jpg'}
{'name': '啵妞的家', 'address': '北京市朝阳区十里堡润枫嘉尚\n ', 'price': '338', 'owner_pic': 'http://image.xiaozhustatic1.com/21/1,0,33,4216,366,366,c589a192.jpg', 'title': '6号线地铁公寓', 'sex': '女', 'pic': 'http://image.xiaozhustatic1.com/00,800,533/6,0,60,2088,1800,1200,3b057da1.jpg'}
.....
总结
- 常用语法
列表 = [变量 for 变量 in range(开始数字，结束数字)]
urls = ["http://bj.xiaozhu.com/search-duanzufang-p{}-0/".format(number) for number in range(1, 10)]- 感觉重要的还是一个思路，函数与函数之间的联系。把关系屡清楚了，编程就简单了
- address这个变量其实最好还是能去除后面的\n，不过暂时没想出来怎么弄