python爬蟲：爬取鏈家深圳全部二手房的詳細信息
阿新 • • 發佈：2018-11-07
data sts rip 二手房 lse area 列表 dom bubuko
1、問題描述：
爬取鏈家深圳全部二手房的詳細信息，並將爬取的數據存儲到CSV文件中
2、思路分析:
(1)目標網址：https://sz.lianjia.com/ershoufang/
(2)代碼結構：
class LianjiaSpider(object): def __init__(self): def getMaxPage(self, url): # 獲取maxPage def parsePage(self, url): # 解析每個page，獲取每個huose的Link def parseDetail(self, url): # 根據Link，獲取每個house的詳細信息
(3) init(self)初始化函數
· hearders用到了fake_useragent庫，用來隨機生成請求頭。
· datas空列表，用於保存爬取的數據。
def __init__(self):
self.headers = {"User-Agent": UserAgent().random}
self.datas = list()(4) getMaxPage()函數
主要用來獲取二手房頁面的最大頁數.
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}‘，通過eval()函數把字符串轉換為字典 maxPage = eval(pageData)["totalPage"] return maxPage else: print("Fail status: {}".format(response.status_code)) return None
(5)parsePage()函數
主要是用來進行翻頁的操作，得到每一頁的所有二手房的Links鏈接。它通過利用一個for循環來重構 url實現翻頁操作，而循環最大頁數就是通過上面的 getMaxPage() 來獲取到。
def parsePage(self, url): maxPage = self.getMaxPage(url) # 解析每個page，獲取每個二手房的鏈接 for pageNum in range(1, maxPage+1 ): url = "https://sz.lianjia.com/ershoufang/pg{}/".format(pageNum) print("當前正在爬取: {}".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"] #每個<info clear>標簽有很多<a>,而我們只需要第一個，所以用find detail = self.parseDetail(link) self.datas.append(detail)
(6)parseDetail()函數
根據parsePage()函數獲取的二手房Link鏈接，向該鏈接發送請求，獲取出詳細頁面信息。
def parseDetail(self, url):
response = requests.get(url, headers = self.headers)
detail = {}
if response.status_code == 200:
soup = BeautifulSoup(response.text, "html.parser")
detail["價格"] = soup.find("span", class_ = "total").text
detail["單價"] = soup.find("span", class_ = "unitPriceValue").text
detail["小區"] = soup.find("div", class_ = "communityName").find("a", class_ = "info").text
detail["位置"] = soup.find("div", class_="areaName").find("span", class_="info").text
detail["地鐵"] = soup.find("div", class_="areaName").find("a", class_="supplement").text
base = soup.find("div", class_ = "base").find_all("li") # 基本信息
detail["戶型"] = base[0].text[4:]
detail["面積"] = base[2].text[4:]
detail["朝向"] = base[6].text[4:]
detail["電梯"] = base[10].text[4:]
return detail
else:
return None(7)將數據存儲到CSV文件中
這裏用到了 pandas 庫的 DataFrame() 方法，它默認的是按照列名的字典順序排序的。想要自定義列的順序，可以加columns字段。
# 將所有爬取的二手房數據存儲到csv文件中
data = pd.DataFrame(self.datas)
# columns字段：自定義列的順序（DataFrame默認按列名的字典序排序）
columns = ["小區", "戶型", "面積", "價格", "單價", "朝向", "電梯", "位置", "地鐵"]
data.to_csv(".\Lianjia_II.csv", encoding=‘utf_8_sig‘, index=False, columns=columns)3、效果展示
4、完整代碼：
# -* coding: utf-8 *-
#author: wangshx6
#data: 2018-11-07
#descriptinon: 爬取鏈家深圳全部二手房的詳細信息，並將爬取的數據存儲到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}‘，通過eval()函數把字符串轉換為字典
maxPage = eval(pageData)["totalPage"]
return maxPage
else:
print("Fail status: {}".format(response.status_code))
return None
def parsePage(self, url):
maxPage = self.getMaxPage(url)
# 解析每個page，獲取每個二手房的鏈接
for pageNum in range(1, maxPage+1 ):
url = "https://sz.lianjia.com/ershoufang/pg{}/".format(pageNum)
print("當前正在爬取: {}".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"] #每個<info clear>標簽有很多<a>,而我們只需要第一個，所以用find
detail = self.parseDetail(link)
self.datas.append(detail)
# 將所有爬取的二手房數據存儲到csv文件中
data = pd.DataFrame(self.datas)
# columns字段：自定義列的順序（DataFrame默認按列名的字典序排序）
columns = ["小區", "戶型", "面積", "價格", "單價", "朝向", "電梯", "位置", "地鐵"]
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["價格"] = soup.find("span", class_ = "total").text
detail["單價"] = soup.find("span", class_ = "unitPriceValue").text
detail["小區"] = soup.find("div", class_ = "communityName").find("a", class_ = "info").text
detail["位置"] = soup.find("div", class_="areaName").find("span", class_="info").text
detail["地鐵"] = soup.find("div", class_="areaName").find("a", class_="supplement").text
base = soup.find("div", class_ = "base").find_all("li") # 基本信息
detail["戶型"] = base[0].text[4:]
detail["面積"] = base[2].text[4:]
detail["朝向"] = base[6].text[4:]
detail["電梯"] = base[10].text[4:]
return detail
else:
return None
if __name__ == "__main__":
Lianjia = LianjiaSpider()
Lianjia.parsePage("https://sz.lianjia.com/ershoufang/")python爬蟲：爬取鏈家深圳全部二手房的詳細信息