Python爬蟲爬取房天下數據-入MySql數據庫

Python爬取房天下某城市數據

隨着互聯網時代的興起，技術日新月異，掌握一門新技術對職業發展有着很深遠的意義，做的第一個demo，以后會在爬蟲和數據分析方便做更深的研究，本人不會做詳細的文檔，有哪里不足的地方，希望大牛們指點講解。廢話不多說，上代碼。

你需要的技能：

（1）對前端知識熟悉會調試瀏覽器

（2）熟練python基礎知識，對一些常用的庫熟練掌握

（3）掌握一般關系型數據庫

import requests as req
import time
import pandas as pd
from bs4 import BeautifulSoup
from sqlalchemy import create_engine

global info
def getHouseInfo(url):
	info = {}
	soup = BeautifulSoup(req.get(url).text,"html.parser")
	resinfo = soup.select(".tab-cont-right .trl-item1")

	# 獲取戶型、建築面積、單價、朝向、樓層、裝修情況
	for re in resinfo:
		tmp = re.text.strip().split("\n")
		name = tmp[1].strip()
		if("朝向" in name):
			name = name.strip("進門")
		if("樓層" in name):
			name = name[0:2]
		if("地上層數" in name):
			name = "樓層"
		if("裝修程度" in name):
			name = "裝修"
		info[name] = tmp[0].strip()

	xiaoqu = soup.select(".rcont .blue")[0].text.strip()
	info["小區名字"] = xiaoqu
	zongjia = soup.select(".tab-cont-right .trl-item")
	info["總價"] = zongjia[0].text
	return info

domain = "http://esf.anyang.fang.com/"
city = "house/"
#獲取總頁數
def getTotalPage():
	res = req.get(domain+city+"i31")
	soup = BeautifulSoup(res.text, "html.parser")
	endPage = soup.select(".page_al a").pop()['href']
	pageNum = endPage.strip("/").split("/")[1].strip("i3")
	print("loading.....總共 "+pageNum+" 頁數據.....")
	return pageNum

# 分頁爬取數據
def pageFun(i):
	pageUrl = domain + city + "i3" +i
	print(pageUrl+" loading...第 "+i+" 頁數據.....")
	res = req.get(pageUrl)
	soup = BeautifulSoup(res.text,"html.parser")
	houses = soup.select(".shop_list dl")
	pageInfoList = []
	for house in houses:
		try:
			# print(domain + house.select("a")[0]['href'])
			info = getHouseInfo(domain + house.select("a")[0]['href'])
			pageInfoList.append(info)
			print(info)
		except Exception as e:
			print("---->出現異常，跳過 繼續執行",e)

	df =  pd.DataFrame(pageInfoList)
	return df

connect = create_engine("mysql+pymysql://root:root@localhost:3306/houseinfo?charset=utf8")

for i in range(1,int(getTotalPage())+1):
	try:
		df_onePage = pageFun(str(i))
	except Exception as e:
		print("Exception",e)
	pd.io.sql.to_sql(df_onePage, "city_house_price", connect, schema="houseinfo", if_exists="append")