from bs4 import BeautifulSoup

import pandas as pd

import requests

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'}

獲取一級代碼、名稱、下一級鏈接

通過設置參數originUrl來調整爬取的年份

def getOneLevelCodeName(originUrl = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2019/index.html'):

web = requests.get(originUrl,headers=headers) #獲取網頁

web.encoding = web.apparent_encoding #設置編碼

soup = BeautifulSoup(web.text,'html.parser') #解析網頁

provinceList = soup.select('.provincetr') #查找類名為provincetr的內容

oneLevelWeb = []

for table in provinceList:

for province in table.select('a'):

oneLevelWeb.append((province['href'],province.text))#獲取下一級短鏈接、獲取省名

oneLevelWebUrl = [(url[0][0:2]+'0000000000','中國-'+url[1],originUrl[0:54]+url[0]) for url in oneLevelWeb] #構建區劃代碼、省名、下一級鏈接

return oneLevelWebUrl

獲取二級代碼、名稱、下一級鏈接

#根據一級鏈接，獲取下一級

def getSecodLevelCodeName(proLevelName=None,url='None'):

if proLevelName is None or url == 'None':

pass

else:

web = requests.get(url,headers=headers)

web.encoding = web.apparent_encoding

soup = BeautifulSoup(web.text,'html.parser')

secondLevelCodeNameList = soup.select('.citytr')

retList = []

for tag in secondLevelCodeNameList:

if tag.text[12:] == '市轄區':

retList.append((tag.text[0:12],proLevelName+'-'+proLevelName.split('-')[-1]+tag.text[12:],url[0:54]+tag.select('a')[0]['href']))

else:

retList.append((tag.text[0:12],proLevelName+'-'+tag.text[12:],url[0:54]+tag.select('a')[0]['href']))

return retList

獲取三級代碼、名稱、下一級鏈接

#根據二級鏈接，獲取下一級

def getThirdLevelCodeName(proLevelName=None,url='None'):

if proLevelName is None or url == 'None':

pass

else:

web = requests.get(url,headers=headers)

web.encoding = web.apparent_encoding

soup = BeautifulSoup(web.text,'html.parser')

thirdLevelCodeNameList = soup.select('.countytr')

retList = []

for tag in thirdLevelCodeNameList:

try:

retList.append((tag.text[0:12],proLevelName+'-'+tag.text[12:],url[0:56]+'/'+tag.select('a')[0]['href']))

except:

retList.append((tag.text[0:12],proLevelName+'-'+proLevelName.split('-')[-1]+tag.text[12:],'None'))

return retList

獲取四級代碼、名稱、下一級鏈接

#根據三級鏈接，獲取下一級

def getFourthLevelCodeName(proLevelName=None,url='None'):

if proLevelName is None or url == 'None':

pass

else:

web = requests.get(url,headers=headers)

web.encoding = web.apparent_encoding

soup = BeautifulSoup(web.text,'html.parser')

fourthLevelCodeNameList = soup.select('.towntr')

retList = []

for tag in fourthLevelCodeNameList:

retList.append((tag.text[0:12],proLevelName+'-'+tag.text[12:],url[0:60]+tag.select('a')[0]['href']))

return retList

轉為DataFrame，輸出excel文件

pd_oneLevel = pd.DataFrame(oneLevel)

pd_oneLevel

pd_secondLevel = pd.concat([pd.DataFrame(data) for data in secondLevel])

pd_secondLevel

pd_thirdLevel = pd.concat([pd.DataFrame(data) for data in thirdLevel])

pd_thirdLevel

pd_fourthLevel = pd.concat([pd.DataFrame(data) for data in fourthLevel])

pd_fourthLevel

pd_allLevel = pd.concat([pd_oneLevel,pd_secondLevel,pd_thirdLevel,pd_fourthLevel],ignore_index=True)

pd_allLevel.columns = ['區劃代碼','名稱','下一級網址']

pd_allLevel

保存到當前目錄

import os

pd_allLevel.to_excel(r''+os.path.realpath('__file__')[0:-8]+'2018區劃代碼及名稱.xlsx',index=False)

創作挑戰賽新人創作獎勵來咯，堅持創作打卡瓜分現金大獎

總結

以上是生活随笔為你收集整理的php抓取统计局区划代码,抓取国家统计局的代码和名称,爬取,区域,划分,及的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。