百度地图迁徙链接为 ：https://qianxi.baidu.com/
建议尽早爬取数据，以后可能会关闭
python爬虫的代码
import os
import random
import time
from urllib import request
import re
import requests
import xlwt
from utils.read_write import readTXT, writeOneJSON
os.chdir(r'D:\data\人口数据\百度迁徙大数据\全国城市省份市内流入流出\json')
def set_style(name, height, bold=False):
style = xlwt.XFStyle() # 初始化样式
font = xlwt.Font() # 为样式创建字体
font.name = name # 'Times New Roman'
font.bold = bold
font.color_index = 4
font.height = height
style.font = font
return style
f = xlwt.Workbook()
sheet2 = f.add_sheet(u'sheet2', cell_overwrite_ok=True) # 创建sheet2
row0 = [u'迁入城市',u'所在城市',u'占比',u'迁出城市',u'所在城市',u'占比',u'迁入省份',u'所在城市',u'占比',u'迁出省份',u'所在城市',u'占比']
# 生成第一行
for i in range(0, len(row0)):
sheet2.write(0, i, row0[i], set_style('Times New Roman', 200, True))
headers = {"User-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 "
"(KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0"}
opener = request.build_opener()
opener.add_headers = [headers]
request.install_opener(opener)
default = set_style('Times New Roman', 220)
date_list = []
lines = readTXT('D:\project\jianguiyuan\data\BaiduMap_cityCode_1102.txt')
for riqi in range(20200103, 20200132):
date_list.append(str(riqi))
for riqi in range(20200201, 20200226):
date_list.append(str(riqi))
for riqi in date_list:
print(riqi)
for i in range(1, 389):
print(i)
obj = lines[i].split(',')
print(obj[0])
print(obj[1])
firsturl = "http://huiyan.baidu.com/migration/cityrank.jsonp?dt=country&id=" + obj[0] + "&type=move_in&date=" + riqi + "&callback=jsonp"
randint_data = random.randint(3, 6)
time.sleep(randint_data)
data = request.urlopen(firsturl).read().decode("utf-8")
data = data.encode("utf-8").decode("unicode_escape")
writeOneJSON(data, "城市迁入_" +obj[1] + "_" +riqi + ".json")
# 对Unicode编码进行改造
pat = '{"city_name":"(.*?)","province_name":".*?","value":.*?}'
pat1 = '{"city_name":".*?","province_name":".*?","value":(.*?)}'
result = re.compile(pat).findall(str(data))
result1 = re.compile(pat1).findall(str(data))
column0 = result
column1 = result1
column2 = obj[1]
for i1 in range(0, len(column0)):
sheet2.write(i1 + len(column0) * i + 1, 0, column0[i1], default)
for i1 in range(0, len(column0)):
sheet2.write(i1 + len(column0) * i + 1, 1, column2, default)
for i1 in range(0, len(column1)):
sheet2.write(i1 + len(column0) * i + 1, 2, column1[i1], default)
firsturl = "http://huiyan.baidu.com/migration/cityrank.jsonp?dt=country&" \
"id="+obj[0]+"&type=move_out&date="+ riqi+"&callback=jsonp"
randint_data = random.randint(3, 7)
time.sleep(randint_data)
data2 = request.urlopen(firsturl).read().decode("utf-8")
data2 = data2.encode("utf-8").decode("unicode_escape") #
writeOneJSON(data2, "城市迁出_" + obj[1] + "_" + riqi + ".json")
#对Unicode编码进行改造
pat = '{"city_name":"(.*?)","province_name":".*?","value":.*?}'
pat1 = '{"city_name":".*?","province_name":".*?","value":(.*?)}'
result2 = re.compile(pat).findall(str(data2))
result12 = re.compile(pat1).findall(str(data2))
column0 = result2
column1 = result12
column2 = obj[1]
for i1 in range(0, len(column0)):
sheet2.write(i1 + len(column0) * i + 1, 3, column0[i1], default)
for i1 in range(0, len(column0)):
sheet2.write(i1 + len(column0) * i + 1, 4, column2, default)
for i1 in range(0, len(column1)):
sheet2.write(i1 + len(column0) * i + 1, 5, column1[i1], default)
firsturl = "http://huiyan.baidu.com/migration/provincerank.jsonp?dt=country&id=" +obj[0] + "&type=move_in&date=" + riqi + "&callback=jsonp"
randint_data = random.randint(3, 8)
time.sleep(randint_data)
data = request.urlopen(firsturl).read().decode("utf-8")
data = data.encode("utf-8").decode("unicode_escape")
writeOneJSON(data, "省份迁入_" + obj[1] + "_" + riqi + ".json")
# 对Unicode编码进行改造
pat = '{"province_name":(.*?),"value":.*?}'
pat1 = '{"province_name":".*?","value":(.*?)}'
result = re.compile(pat).findall(str(data))
result1 = re.compile(pat1).findall(str(data))
column0 = result
column1 = result1
column2 = obj[1]
for i1 in range(0, len(column0)):
sheet2.write(i1 + len(column0) * i + 1, 6, column0[i1], default)
for i1 in range(0, len(column0)):
sheet2.write(i1 + len(column0) * i + 1, 7, column2, default)
for i1 in range(0, len(column1)):
sheet2.write(i1 + len(column0) * i + 1, 8, column1[i1], default)
firsturl = "http://huiyan.baidu.com/migration/provincerank.jsonp?dt=country&" \
"id="+obj[0]+"&type=move_out&date="+ riqi+"&callback=jsonp"
randint_data = random.randint(3, 6)
time.sleep(randint_data)
data2 = request.urlopen(firsturl).read().decode("utf-8")
data2 = data2.encode("utf-8").decode("unicode_escape") #
writeOneJSON(data2, "省份迁出_" + obj[1] + "_" + riqi + ".json")
#对Unicode编码进行改造
pat = '{"province_name":(.*?),"value":.*?}'
pat1 = '{"province_name":".*?","value":(.*?)}'
result2 = re.compile(pat).findall(str(data2))
result12 = re.compile(pat1).findall(str(data2))
column0 = result2
column1 = result12
column2 = obj[1]
for i1 in range(0, len(column0)):
sheet2.write(i1 + len(column0) * i + 1, 9, column0[i1], default)
for i1 in range(0, len(column0)):
sheet2.write(i1 + len(column0) * i + 1, 10, column2, default)
for i1 in range(0, len(column1)):
sheet2.write(i1 + len(column0) * i + 1, 11, column1[i1], default)
print("大吉大利，今晚吃鸡啊！")
filename = 'D:\data\人口数据\百度迁徙大数据\全国城市省份市内流入流出\\'+riqi+'.xls'
f.save(filename)
其中涉及到的文件下载请点击
我的资源
read_write.py文件链接：
python读写文件
百度城市编码文件：
城市编码
如需全国所有城市的城内出行强度数据、迁入地来源和迁出目的地数据
请私聊我获取联系方式
