1、问题描述:
爬取链家深圳全部二手房的详细信息,并将爬取的数据存储到csv文件中
2、思路分析:
(1)目标网址:
(2)代码结构:
class lianjiaspider(object):
def __init__(self):
def getmaxpage(self, url): # 获取maxpage
def parsepage(self, url): # 解析每个page,获取每个huose的link
def parsedetail(self, url): # 根据link,获取每个house的详细信息
(3) init(self)初始化函数
· hearders用到了fake_useragent库,用来随机生成请求头。
· datas空列表,用于保存爬取的数据。
def __init__(self):
self.headers = {"user-agent": useragent().random}
self.datas = list()
(4) getmaxpage()函数
主要用来获取二手房页面的最大页数.
def getmaxpage(self, url):
response = requests.get(url, headers = self.headers)
if response.status_code == 200:
source = response.text
soup = beautifulsoup(source, "html.parser")
pagedata = soup.find("div", class_ = "page-box house-lst-page-box")["page-data"]
# pagedata = '{"totalpage":100,"curpage":1}',通过eval()函数把字符串转换为字典
maxpage = eval(pagedata)["totalpage"]
return maxpage
else:
print("fail status: {}".format(response.status_code))
return none
(5)parsepage()函数
主要是用来进行翻页的操作,得到每一页的所有二手房的links链接。它通过利用一个for循环来重构 url实现翻页操作,而循环最大页数就是通过上面的 getmaxpage() 来获取到。
def parsepage(self, url):
maxpage = self.getmaxpage(url)
# 解析每个page,获取每个二手房的链接
for pagenum in range(1, maxpage+1 ):
url = "https://sz.lianjia.com/ershoufang/pg{}/".format(pagenum)
print("当前正在爬取: {}".format(url))
response = requests.get(url, headers = self.headers)
soup = beautifulsoup(response.text, "html.parser")
links = soup.find_all("div", class_ = "info clear")
for i in links:
link = i.find("a")["href"] #每个标签有很多,而我们只需要第一个,所以用find
detail = self.parsedetail(link)
self.datas.append(detail)
(6)parsedetail()函数
根据parsepage()函数获取的二手房link链接,向该链接发送请求,获取出详细页面信息。
def parsedetail(self, url):
response = requests.get(url, headers = self.headers)
detail = {}
if response.status_code == 200:
soup = beautifulsoup(response.text, "html.parser")
detail["价格"] = soup.find("span", class_ = "total").text
detail["单价"] = soup.find("span", class_ = "unitpricevalue").text
detail["小区"] = soup.find("div", class_ = "communityname").find("a", class_ = "info").text
detail["位置"] = soup.find("div", class_="areaname").find("span", class_="info").text
detail["地铁"] = soup.find("div", class_="areaname").find("a", class_="supplement").text
base = soup.find("div", class_ = "base").find_all("li") # 基本信息
detail["户型"] = base[0].text[4:]
detail["面积"] = base[2].text[4:]
detail["朝向"] = base[6].text[4:]
detail["电梯"] = base[10].text[4:]
return detail
else:
return none
(7)将数据存储到csv文件中
这里用到了 pandas 库的 dataframe() 方法,它默认的是按照列名的字典顺序排序的。想要自定义列的顺序,可以加columns字段。
# 将所有爬取的二手房数据存储到csv文件中
data = pd.dataframe(self.datas)
# columns字段:自定义列的顺序(dataframe默认按列名的字典序排序)
columns = ["小区", "户型", "面积", "价格", "单价", "朝向", "电梯", "位置", "地铁"]
data.to_csv(".\lianjia_ii.csv", encoding='utf_8_sig', index=false, columns=columns)
3、效果展示
4、完整代码:
# -* coding: utf-8 *-
#author: wangshx6
#data: 2018-11-07
#descriptinon: 爬取链家深圳全部二手房的详细信息,并将爬取的数据存储到csv文
import requests
from bs4 import beautifulsoup
import pandas as pd
from fake_useragent import useragent
class lianjiaspider(object):
def __init__(self):
self.headers = {"user-agent": useragent().random}
self.datas = list()
def getmaxpage(self, url):
response = requests.get(url, headers = self.headers)
if response.status_code == 200:
source = response.text
soup = beautifulsoup(source, "html.parser")
pagedata = soup.find("div", class_ = "page-box house-lst-page-box")["page-data"]
# pagedata = '{"totalpage":100,"curpage":1}',通过eval()函数把字符串转换为字典
maxpage = eval(pagedata)["totalpage"]
return maxpage
else:
print("fail status: {}".format(response.status_code))
return none
def parsepage(self, url):
maxpage = self.getmaxpage(url)
# 解析每个page,获取每个二手房的链接
for pagenum in range(1, maxpage+1 ):
url = "https://sz.lianjia.com/ershoufang/pg{}/".format(pagenum)
print("当前正在爬取: {}".format(url))
response = requests.get(url, headers = self.headers)
soup = beautifulsoup(response.text, "html.parser")
links = soup.find_all("div", class_ = "info clear")
for i in links:
link = i.find("a")["href"] #每个标签有很多,而我们只需要第一个,所以用find
detail = self.parsedetail(link)
self.datas.append(detail)
# 将所有爬取的二手房数据存储到csv文件中
data = pd.dataframe(self.datas)
# columns字段:自定义列的顺序(dataframe默认按列名的字典序排序)
columns = ["小区", "户型", "面积", "价格", "单价", "朝向", "电梯", "位置", "地铁"]
data.to_csv(".\lianjia_ii.csv", encoding='utf_8_sig', index=false, columns=columns)
def parsedetail(self, url):
response = requests.get(url, headers = self.headers)
detail = {}
if response.status_code == 200:
soup = beautifulsoup(response.text, "html.parser")
detail["价格"] = soup.find("span", class_ = "total").text
detail["单价"] = soup.find("span", class_ = "unitpricevalue").text
detail["小区"] = soup.find("div", class_ = "communityname").find("a", class_ = "info").text
detail["位置"] = soup.find("div", class_="areaname").find("span", class_="info").text
detail["地铁"] = soup.find("div", class_="areaname").find("a", class_="supplement").text
base = soup.find("div", class_ = "base").find_all("li") # 基本信息
detail["户型"] = base[0].text[4:]
detail["面积"] = base[2].text[4:]
detail["朝向"] = base[6].text[4:]
detail["电梯"] = base[10].text[4:]
return detail
else:
return none
if __name__ == "__main__":
lianjia = lianjiaspider()
lianjia.parsepage("https://sz.lianjia.com/ershoufang/")
如您对本文有疑问或者有任何想说的,请点击进行留言回复,万千网友为您解惑!