selenium爬取中国经济与社会发展统计数据库

声明:代码仅作学习交流用途,代码分享者与创作者不承担任何由他人恶意运行而导致的责任,勿擅自修改限制频率的参数,勿恶意攻击网页,请学习浏览者遵守社会公德与法律秩序,爬虫导致的网页崩溃等损失由计算机操作者负全部责任,造成严重后果的需要承担刑事责任
爬虫代写:邮箱 leon_leon@yeah.net


from selenium import webdriver
from time import sleep
from lxml import etree
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import Select
import pandas as pd
from random import randint
edge = webdriver.Edge()

edge.get("https://data.cnki.net/NewHome/Index")
#edge.find_element_by_id("Button2").click()
#edge.find_element_by_href("/Area/Home/Index/D12").click()
edge.find_element(By.XPATH, '/html/body/div[1]/div[4]/ul/li[2]/a').click()
sleep(6)
for handle in edge.window_handles:#方法二,始终获得当前最后的窗口
    edge.switch_to.window(handle)

year = [str(i) for i in range(1994,2015)]
month = [str(i) for i in range(1,13)]
for year_index,year_item in enumerate(year):
    Select(edge.find_element(By.ID, "selYear")).select_by_value(year_item)
    sleep(randint(5,9))
    for month_index,month_item in enumerate(month):
        print('已成功获取{}%数据'.format(((1+year_index)*12+(month_index+1))/252*100))
#        edge.find_element(By.XPATH, '//*[@id="J_headroom-n"]/div/a[9]').click()
        edge.find_element(By.XPATH, '''//div[@id='J_conNav09']/div/ul/li[@class='item'][1]/a[@mval={}]'''.format(month_item)).click()
        sleep(randint(10,13))
        for handle in edge.window_handles:  # 方法二,始终获得当前最后的窗口
            edge.switch_to.window(handle)
        html = edge.page_source
        # print(html)
        e = etree.HTML(html)
        row_name = e.xpath('//tbody/tr[position()>2]/td[1]/text()')
        data = e.xpath('//tbody/tr[position()>2]/td[position()>1]/span/text()')
        column_name = e.xpath('//tbody/tr[2]/td/text()')
        df = pd.DataFrame(index=row_name, columns=column_name)
        row_num = len(row_name)
        col_num = len(column_name)
        for i in range(row_num):
            for j in range(col_num):
                df.iloc[i,j] = data[i*col_num + j]
        df.to_csv('{0}年{1}月进出口数据.csv'.format(year_item,month_item), encoding='GBK')
        edge.close()
        handles = edge.window_handles
        edge.switch_to.window(handles[1])


from selenium import webdriver
from time import sleep
from lxml import etree
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import Select
import pandas as pd
from random import randint
edge = webdriver.Edge()

edge.get("https://data.cnki.net/NewHome/Index")
#edge.find_element_by_id("Button2").click()
#edge.find_element_by_href("/Area/Home/Index/D12").click()
edge.find_element(By.XPATH, '/html/body/div[1]/div[4]/ul/li[2]/a').click()
sleep(6)
for handle in edge.window_handles:#方法二,始终获得当前最后的窗口
    edge.switch_to.window(handle)

year = [str(i) for i in range(1994,2015)]
month = [str(i) for i in range(1,13)]
for year_index,year_item in enumerate(year):
    if edge.find_element(By.ID,"Button2").is_displayed():
        edge.find_element(By.ID,"Button2").click()
    Select(edge.find_element(By.ID, "selYear")).select_by_value(year_item)
    sleep(randint(5, 9))
    for month_index,month_item in enumerate(month):
        print('已成功获取{}%数据'.format(((1+year_index)*12+(month_index+1))/252*100))
#        edge.find_element(By.XPATH, '//*[@id="J_headroom-n"]/div/a[9]').click()
        if edge.find_element(By.ID, "Button2").is_displayed():
            edge.find_element(By.ID, "Button2").click()
        edge.find_element(By.XPATH, '''//div[@id='J_conNav09']/div/ul/li[@class='item'][1]/a[@mval={}]'''.format(month_item)).click()
        sleep(randint(10,13))
        for handle in edge.window_handles:  # 方法二,始终获得当前最后的窗口
            edge.switch_to.window(handle)
        html = edge.page_source
        # print(html)
        e = etree.HTML(html)
        row_name = e.xpath('//tbody/tr[position()>2]/td[1]/text()')
        data = e.xpath('//tbody/tr[position()>2]/td[position()>1]/span/text()')
        column_name = e.xpath('//tbody/tr[2]/td/text()')
        df = pd.DataFrame(index=row_name, columns=column_name)
        row_num = len(row_name)
        col_num = len(column_name)
        for i in range(row_num):
            for j in range(col_num):
                df.iloc[i,j] = data[i*col_num + j]
        df.to_csv('{0}年{1}月进出口数据.csv'.format(year_item,month_item), encoding='GBK')
        edge.close()
        handles = edge.window_handles
        edge.switch_to.window(handles[1])


year = [str(i) for i in range(2020,2014,-1)]
month = [str(i) for i in range(1,13)]
for year_index,year_item in enumerate(year):
    if edge.find_element(By.ID,"Button2").is_displayed():
        edge.find_element(By.ID,"Button2").click()
    edge.find_element(By_XPATH,'//*[@id="J_headroom"]/div[2]/div/a[{}]'.format(year_index+1)).click()
    sleep(randint(5, 9))
    for month_index,month_item in enumerate(month):
        print('已成功获取{0},{1}%数据'.format(year_item,month_item))
#        edge.find_element(By.XPATH, '//*[@id="J_headroom-n"]/div/a[9]').click()
        if edge.find_element(By.ID, "Button2").is_displayed():
            edge.find_element(By.ID, "Button2").click()
        edge.find_element(By.XPATH, '''//div[@id='J_conNav09']/div/ul/li[@class='item'][1]/a[@mval={}]'''.format(month_item)).click()
        sleep(randint(10,13))
        for handle in edge.window_handles:  # 方法二,始终获得当前最后的窗口
            edge.switch_to.window(handle)
        html = edge.page_source
        # print(html)
        e = etree.HTML(html)
        row_name = e.xpath('//tbody/tr[position()>2]/td[1]/text()')
        data = e.xpath('//tbody/tr[position()>2]/td[position()>1]/span/text()')
        column_name = e.xpath('//tbody/tr[2]/td/text()')
        df = pd.DataFrame(index=row_name, columns=column_name)
        row_num = len(row_name)
        col_num = len(column_name)
        for i in range(row_num):
            for j in range(col_num):
                df.iloc[i,j] = data[i*col_num + j]
        df.to_csv('{0}年{1}月进出口数据.csv'.format(year_item,month_item), encoding='GBK')
        edge.close()
        handles = edge.window_handles
        edge.switch_to.window(handles[1])
print('爬虫100%')
from selenium import webdriver
from time import sleep
from lxml import etree
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import Select
import pandas as pd
from random import randint
edge = webdriver.Edge()

edge.get("https://data.cnki.net/NewHome/Index")
#edge.find_element_by_id("Button2").click()
#edge.find_element_by_href("/Area/Home/Index/D12").click()
edge.find_element(By.XPATH, '/html/body/div[1]/div[4]/ul/li[2]/a').click()
sleep(6)
for handle in edge.window_handles:#方法二,始终获得当前最后的窗口
    edge.switch_to.window(handle)

year = [str(i) for i in range(1995,2015)]
month = [str(i) for i in range(1,13)]
for year_index,year_item in enumerate(year):
    Select(edge.find_element(By.ID, "selYear")).select_by_value(year_item)
    sleep(randint(4, 6))
    for month_index,month_item in enumerate(month):
        print('已成功获取{0}年{1}月数据'.format(year_item,month_item))
#        edge.find_element(By.XPATH, '//*[@id="J_headroom-n"]/div/a[9]').click()
   #     if edge.find_element(By.ID, "Button2").is_displayed():
   #         edge.find_element(By.ID, "Button2").click()
        edge.find_element(By.XPATH, '''//div[@id='J_conNav09']/div/ul/li[@class='item'][1]/a[@mval={}]'''.format(month_item)).click()
        sleep(randint(7,10))
        for handle in edge.window_handles:  # 方法二,始终获得当前最后的窗口
            edge.switch_to.window(handle)
        html = edge.page_source
        # print(html)
        e = etree.HTML(html)
        row_name = e.xpath('//tbody/tr[position()>2]/td[1]/text()')
        data = e.xpath('//tbody/tr[position()>2]/td[position()>1]//text()')
        column_name = e.xpath('//tbody/tr[2]/td/text()')
        df = pd.DataFrame(index=row_name, columns=column_name)
        row_num = len(row_name)
        col_num = len(column_name)
        for i in range(row_num):
            for j in range(col_num):
                df.iloc[i,j] = data[i*col_num + j]
        df.to_csv('{0}年{1}月进出口数据.csv'.format(year_item,month_item), encoding='GBK')
        edge.close()
        handles = edge.window_handles
        edge.switch_to.window(handles[1])


year = [str(i) for i in range(2020,2014,-1)]
month = [str(i) for i in range(1,13)]
for year_index,year_item in enumerate(year):
  #  if edge.find_element(By.ID,"Button2").is_displayed():
    #    edge.find_element(By.ID,"Button2").click()
    edge.find_element(By_XPATH,'//*[@id="J_headroom"]/div[2]/div/a[{}]'.format(year_index+1)).click()
    sleep(randint(5, 9))
    for month_index,month_item in enumerate(month):
        print('已成功获取{0}年,{1}月数据'.format(year_item,month_item))
#        edge.find_element(By.XPATH, '//*[@id="J_headroom-n"]/div/a[9]').click()
   #     if edge.find_element(By.ID, "Button2").is_displayed():
    #        edge.find_element(By.ID, "Button2").click()
        edge.find_element(By.XPATH, '''//div[@id='J_conNav09']/div/ul/li[@class='item'][1]/a[@mval={}]'''.format(month_item)).click()
        sleep(randint(5,7))
        for handle in edge.window_handles:  # 方法二,始终获得当前最后的窗口
            edge.switch_to.window(handle)
        html = edge.page_source
        # print(html)
        e = etree.HTML(html)
        row_name = e.xpath('//tbody/tr[position()>2]/td[1]/text()')
        data = e.xpath('//tbody/tr[position()>2]/td[position()>1]/span/text()')
        column_name = e.xpath('//tbody/tr[2]/td/text()')
        df = pd.DataFrame(index=row_name, columns=column_name)
        row_num = len(row_name)
        col_num = len(column_name)
        for i in range(row_num):
            for j in range(col_num):
                df.iloc[i,j] = data[i*col_num + j]
        df.to_csv('{0}年{1}月进出口数据.csv'.format(year_item,month_item), encoding='GBK')
        edge.close()
        handles = edge.window_handles
        edge.switch_to.window(handles[1])
print('爬虫100%')
爬虫(Web Crawler)是一种自动化程序,用于从互联网上收集信息。其主要功能是访问网页、提取数据并存储,以便后续分析或展示。爬虫通常由搜索引擎、数据挖掘工具、监测系统等应用于网络数据抓取的场景。 爬虫的工作流程包括以下几个关键步骤: URL收集: 爬虫从一个或多个初始URL开始,递归或迭代地发现新的URL,构建一个URL队列。这些URL可以通过链接分析、站点地图、搜索引擎等方式获取。 请求网页: 爬虫使用HTTP或其他协议向目标URL发起请求,获取网页的HTML内容。这通常通过HTTP请求库实现,如Python中的Requests库。 解析内容: 爬虫对获取的HTML进行解析,提取有用的信息。常用的解析工具有正则表达式、XPath、Beautiful Soup等。这些工具帮助爬虫定位和提取目标数据,如文本、图片、链接等。 数据存储: 爬虫将提取的数据存储到数据库、文件或其他存储介质中,以备后续分析或展示。常用的存储形式包括关系型数据库、NoSQL数据库、JSON文件等。 遵守规则: 为避免对网站造成过大负担或触发反爬虫机制,爬虫需要遵守网站的robots.txt协议,限制访问频率和深度,并模拟人类访问行为,如设置User-Agent。 反爬虫应对: 由于爬虫的存在,一些网站采取了反爬虫措施,如验证码、IP封锁等。爬虫工程师需要设计相应的策略来应对这些挑战。 爬虫在各个领域都有广泛的应用,包括搜索引擎索引、数据挖掘、价格监测、新闻聚合等。然而,使用爬虫需要遵守法律和伦理规范,尊重网站的使用政策,并确保对被访问网站的服务器负责。
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

小蜗笔记

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值