前言：
- 提前安装好所需要的库。
- 本代码的输入仅需要某个城市的租房地址首页即可，其他自会生成。
- 使用前请创建所需的目录，或者为代码添加os.makedir()
- 支持断点重爬，重行运行即可。
- headers等随运行环境不同，可能需要进行修改。
- 本代码使用了高德API key，用于获取地理坐标，但发布时已略去，如需使用，请注册高德api开发者。
- 内容原创，引用请注明出处。Note: http://www.cnblogs.com/shadrach; author: [email protected]。
# author: [email protected]
# blog: http://www.cnblogs.com/shadrach
# NOTE: original article, indicate the source if reprint.
# Thanks.
# Update: 2018/1/24
import urllib.request
from bs4 import BeautifulSoup
import xlsxwriter
import xlrd
import os
import math
import time
import glob # coordinate convert: from gcj(amap) to wgs(gps)
def GCJ2WGS(location):
# location格式如下：locations[1] = "113.923745,22.530824"
lon = float(location[0:location.find(",")])
lat = float(location[location.find(",") + 1:len(location)])
a = 6378245.0 # 克拉索夫斯基椭球参数长半轴a
ee = 0.00669342162296594323 #克拉索夫斯基椭球参数第一偏心率平方
PI = 3.14159265358979324 # 圆周率
# 以下为转换公式
x = lon - 105.0
y = lat - 35.0
# 经度
dLon = 300.0 + x + 2.0 * y + 0.1 * x * x + 0.1 * x * y + 0.1 * math.sqrt(abs(x))
dLon += (20.0 * math.sin(6.0 * x * PI) + 20.0 * math.sin(2.0 * x * PI)) * 2.0 / 3.0
dLon += (20.0 * math.sin(x * PI) + 40.0 * math.sin(x / 3.0 * PI)) * 2.0 / 3.0
dLon += (150.0 * math.sin(x / 12.0 * PI) + 300.0 * math.sin(x / 30.0 * PI)) * 2.0 / 3.0
#维度
dLat = -100.0 + 2.0 * x + 3.0 * y + 0.2 * y * y + 0.1 * x * y + 0.2 * math.sqrt(abs(x))
dLat += (20.0 * math.sin(6.0 * x * PI) + 20.0 * math.sin(2.0 * x * PI)) * 2.0 / 3.0
dLat += (20.0 * math.sin(y * PI) + 40.0 * math.sin(y / 3.0 * PI)) * 2.0 / 3.0
dLat += (160.0 * math.sin(y / 12.0 * PI) + 320 * math.sin(y * PI / 30.0)) * 2.0 / 3.0
radLat = lat / 180.0 * PI
magic = math.sin(radLat)
magic = 1 - ee * magic * magic
sqrtMagic = math.sqrt(magic)
dLat = (dLat * 180.0) / ((a * (1 - ee)) / (magic * sqrtMagic) * PI)
dLon = (dLon * 180.0) / (a / sqrtMagic * math.cos(radLat) * PI)
wgsLon = lon - dLon
wgsLat = lat - dLat
return wgsLon,wgsLat # xlsx files merge
def xlsx_merge(fileLocation,header,filename):
fileList = []
for fileName in glob.glob(fileLocation + "*.xlsx"):
fileList.append(fileName)
fileNum = len(fileList)
matrix = [None] * fileNum
for i in range(fileNum):
fileName = fileList[i]
workBook = xlrd.open_workbook(fileName)
try:
sheet = workBook.sheet_by_index(0)
except Exception as e:
print(e)
nRows = sheet.nrows
matrix[i] = [0]*(nRows - 1)
nCols = sheet.ncols
for m in range(nRows - 1):
matrix[i][m] = [""]* nCols
for j in range(1,nRows):
for k in range(nCols):
matrix[i][j-1][k] = sheet.cell(j,k).value
fileName = xlsxwriter.Workbook(fileLocation + filename + ".xlsx")
sheet = fileName.add_worksheet("merged")
for i in range(len(header)):
sheet.write(0,i,header[i])
rowIndex = 1
for fileIndex in range(fileNum):
for j in range(len(matrix[fileIndex])):
for colIndex in range (len(matrix[fileIndex][j])):
sheet.write(rowIndex,colIndex,matrix[fileIndex][j][colIndex])
rowIndex += 1
print(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) + ": "+ "已完成%d个文件的合并"%fileNum)
fileName.close() # uniform request
def soup_form(url,referer):
headers = {
"Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
# "Accept-Encoding":"gzip, deflate, sdch, br", # 解码错误，注释
"Accept-Language":"zh-CN,zh;q=0.8",
"Cache-Control":"max-age=0",
"Connection":"keep-alive",
"Cookie":"lps=http%3A%2F%2Fwww.anjuke.com%2F%3Fpi%3DPZ-baidu-pc-all-biaoti%7Chttp%3A%2F%2Fbzclk.baidu.com%2Fadrc.php%3Ft%3D06KL00c00fDgzw60mUFU00PpAs0Mhyup00000PkqW-b00000uN71Vj.THvs_oeHEtY0UWdBmy-bIfK15yNBnHfkrjfLnj0sn1bdmWD0IHYLfbcsnYuKwj-7f1KKfHT4nj0sPYRvwj0dPDFanYFKfsK95gTqFhdWpyfqn103nWfLP1ndniusThqbpyfqnHm0uHdCIZwsT1CEQLILIz49UhGdpvR8mvqVQ1qspHdfyBdBmy-bIidsmzd9UAsVmh-9ULwG0APzm1YkrH6dP0%26tpl%3Dtpl_10085_16624_12226%26l%3D1502510556%26attach%3Dlocation%253D%2526linkName%253D%2525E6%2525A0%252587%2525E9%2525A2%252598%2526linkText%253D%2525E5%2525AE%252589%2525E5%2525B1%252585%2525E5%2525AE%2525A2-%2525E5%25259B%2525BD%2525E5%252586%252585%2525E9%2525A2%252586%2525E5%252585%252588%2525E6%252589%2525BE%2525E6%252588%2525BF%2525E5%2525B9%2525B3%2525E5%25258F%2525B0%2525EF%2525BC%25258C%2525E5%2525AE%252589%2525E5%2525BF%252583%2525E6%25258C%252591%2526xp%253Did%28%252522m4ce5ae35%252522%29%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FH2%25255B1%25255D%25252FA%25255B1%25255D%2526linkType%253D%2526checksum%253D54%26ie%3DUTF-8%26f%3D8%26tn%3Dbaidu%26wd%3D%25E5%25AE%2589%25E5%25B1%2585%25E5%25AE%25A2%26oq%3D%25E5%25AE%2589%25E5%25B1%2585%25E5%25AE%25A2%26rqlang%3Dcn; sessid=CE9A95AF-043B-90B5-A2E4-5F5D39B41EC4; als=0; ctid=41; ANJUKE_BUCKET=pc-home%3AErshou_Web_Home_Home-a; _ga=GA1.2.113488767.1516673325; _gid=GA1.2.255451285.1516673325; __xsptplusUT_8=1; __xsptplus8=8.2.1516678573.1516678593.4%232%7Cbzclk.baidu.com%7C%7C%7C%25E5%25AE%2589%25E5%25B1%2585%25E5%25AE%25A2%7C%23%23249u729XL4J3ZAGKQyEZUyuV4myBLtSZ%23; 58tj_uuid=8a65130f-1085-403a-9e02-5c07dba15641; new_session=0; init_refer=https%253A%252F%252Fnc.zu.anjuke.com%252F%253Ffrom%253Dnavigation; new_uv=2; aQQ_ajkguid=BC9AF129-431B-1C4F-BB91-A27203DE8341; twe=2; Hm_lvt_ed38609fc79dd16e428d5a06610cfeb9=1516673382; Hm_lpvt_ed38609fc79dd16e428d5a06610cfeb9=1516678594",
"Referer":referer,
"Upgrade-Insecure-Requests":"",
"User-Agent":"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36"
}
request = urllib.request.Request(url = url, headers = headers)
soup = BeautifulSoup(urllib.request.urlopen(request,timeout=60).read().decode("utf-8"),"lxml")
return soup header = ["名称","房型","面积","层数","中介人","小区","高德地址","高德坐标","wgs坐标","wgs经度","wgs纬度","路段","地址","特点一","特点二","特点三","价格","房源链接"] # Step1: get and save or read level_1 and level_2 links
links_file = "E:/20180123安居客_南昌租房/links/links.xlsx"
if os.path.exists(links_file):
workbook_links = xlrd.open_workbook(links_file)
sheet_links = workbook_links.sheet_by_index(0)
level2_link = sheet_links.col_values(0)
level2 = sheet_links.col_values(1)
else:
# get sub_level1
url_level_0 = "https://nc.zu.anjuke.com/fangyuan/p1/" # 这个地址是需要根据你所爬取的城市进行修改的
level1_link =[]
level1 = []
for a in soup_form(url_level_0,"https://nc.zu.anjuke.com/").find("div", class_ = "sub-items sub-level1").find_all("a"):
level1_link.append(a.get("href"))
level1.append(a.text) # get sub_level2
level2_link =[]
level2 = []
for i in range(1,len(level1_link)):
for a in soup_form(level1_link[i],level1_link[i-1]).find("div", class_ = "sub-items sub-level2").find_all("a"):
if a.text == "全部":
pass
else:
level2_link.append(a.get("href"))
level2.append(a.text)
workbook_links = xlsxwriter.Workbook(links_file)
sheet_links = workbook_links.add_worksheet("level_2")
sheet_links.write_column(0, 0, level2_link)
sheet_links.write_column(0, 1, level2)
workbook_links.close()
print("Step 1 Done!\nStep 2 Start!") # Step 2: get every level 2 links' rent information
for j in range(len(level2_link)): # at every level 2 page
page_index = 1
for k in range(1,51): # max loop
# at every page, get the max page, and compare to the current page. if more than current page, continue
rent_info_file ="E:/20180123安居客_南昌租房/split_data/" + level2[j] + "_info_page" + str(page_index) + ".xlsx"
if os.path.exists(rent_info_file):
page_index += 1
print(level2[j] + "_info_page" + str(page_index) + ".xlsx already exits")
else:
pages = []
url = level2_link[j] + "p" + str(page_index)
soup = soup_form(url, level2_link[j])
try:
for a in soup.find("div",class_ = "multi-page").find_all("a"):
if a.text == "下一页 >" or a.text == "上一页":
pass
else:
pages.append(int(a.text))
except Exception:
break
try:
max_page = pages[len(pages)-1]
except Exception:
max_page = 1
if page_index < max_page + 2:
workbook_page = xlsxwriter.Workbook(rent_info_file)
sheet = workbook_page.add_worksheet("page" + str(page_index))
for header_index in range(len(header)):
sheet.write(0,header_index,header[header_index])
row_index = 1
for div in soup.find_all("div", class_ = "zu-itemmod"):
try:
sheet.write(row_index,0,div.find("a").get("title")) # 名称
except Exception:
pass try:
sheet.write(row_index,1,div.find("p").text.split("")[0].split("|")[0].replace(" ","").replace("\n","")) # 房型
except Exception:
pass try:
sheet.write(row_index,2,div.find("p").text.split("")[0].split("|")[1]) # 面积
except Exception:
pass try:
sheet.write(row_index,3,div.find("p").text.split("")[0].split("|")[2]) # 层数
except Exception:
pass try:
sheet.write(row_index,4,div.find("p").text.split("")[1]) # 中介人
except Exception:
pass try:
xiaoqu = div.find("address").text.split()[0]
sheet.write(row_index,5,xiaoqu) # 小区
url_amap = "http://restapi.amap.com/v3/geocode/geo?address=" + urllib.parse.quote(xiaoqu) + "&output=xml&city=0791&key=【你的key】"
soup_amap = BeautifulSoup(urllib.request.urlopen(url_amap).read(),"xml")
sheet.write(row_index,6,soup_amap.find("formatted_address").get_text()) # 高德地址
location_amap = soup_amap.find("location").get_text()
sheet.write(row_index,7,location_amap) # 高德坐标
location_wgs = GCJ2WGS(location_amap)
longitude = location_wgs[0]
latitude = location_wgs[1]
sheet.write(row_index,8,str(longitude) + "," + str(latitude)) # wgs坐标
sheet.write(row_index,9,longitude)# wgs经度
sheet.write(row_index,10,latitude) # wgs纬度
except Exception:
pass try:
sheet.write(row_index,11,div.find("address").text.split()[1]) # 路段
except Exception:
pass try:
sheet.write(row_index,12,div.find("address").text.split()[2]) # 地址
except Exception:
pass
try:
sheet.write(row_index,13,div.find("span",class_ = "cls-1").text)
except Exception:
pass try:
sheet.write(row_index,14,div.find("span",class_ = "cls-2").text)
except Exception:
pass try:
sheet.write(row_index,15,div.find("span",class_ = "cls-3").text)
except Exception:
pass try:
sheet.write(row_index,16,div.find("strong").text) # 价格
except Exception:
pass try:
sheet.write(row_index,17,div.find("a").get("href")) # 房源链接
except Exception:
pass
row_index += 1
workbook_page.close()
print(level2[j] + " page" + str(page_index) + " finished")
page_index += 1
else:
break
print(level2[j] + "finished")
print("Step 2 Done!\nStep 3 Start!") # Step 3: merge all xlsx files
xlsx_merge("E:/20180123安居客_南昌租房/split_data/", header, "nanchang_rent_info") print("All work done")