biubiu~你有一份中国人口数据需要查收

爬取世界人口网上的中国各省的2019年人数和2018年GDP

（数据并非完全真实有效）

import requests
import time
from selenium import webdriver
from bs4 import BeautifulSoup
import pandas as pd
from selenium.webdriver.common.action_chains import ActionChains

def get_page(url):
    driver = webdriver.Chrome()
    driver.get(url)
    xpath = '//*[@id="menu-item-9802"]/a'
    ActionChains(driver).click(driver.find_element_by_xpath(xpath)).perform()
    time.sleep(1)
    xpath1 = '//*[@id="copy"]/div[1]'
    table1 = driver.find_element_by_xpath(xpath1).get_attribute('innerHTML')
    soup = BeautifulSoup(table1,'html.parser')
    tb = soup.find_all('tr')
    return tb

def find_message(tb):
    for row in tb:
        cols = [col.text for col in row.find_all('td')]
        if cols[0] == '排名':
            continue
        index.append(cols[0])
        adress.append(cols[1])
        number_2019.append(cols[2])
        GDP_18.append(cols[3])

def save_message():
    data = {'排名':index,'地区':adress,'2019年人口':number_2019,'2018年GDP':GDP_18}
    dataframe = pd.DataFrame(data)
    dataframe.to_csv('Pnumber.csv',index=False,sep=',',encoding='utf-8-sig')

def main():
    tb = get_page(url)
    find_message(tb)
    save_message()

url = 'http://www.chamiji.com'
index = []
adress = []
number_2019 = []
GDP_18 = []
main()