小白用chatgpt编写python 爬虫程序代码 抓取网页数据(js动态生成网页元素)

       如果不加，如果网站有防爬技术，比如频繁访问，后面你会发现什么数据都取不到

User-Agent获取地方：

 网页获取位置：

使用代理IP解决反爬。（免费代理不靠谱，最好使用付费的。有按次数收费的，有按时长收费的，根据自身情况选择）
是什么意思呢，就是每次发送请求，让你像从不同的地域发过来的一样，第一次我的ip地址是河北，第二次是广东，第三次是美国。。。像这样：

def get_ip_pool(cnt):
	"""获取代理ip的函数"""
	url_api = '获取代理IP的API地址'
	try:
		r = requests.get(url_api)
		res_text = r.text
		res_status = r.status_code
		print('获取代理ip状态码：', res_status)
		print('返回内容是：', res_text)
		res_json = json.loads(res_text)
		ip_pool = random.choice(res_json['RESULT'])
		ip = ip_pool['ip']
		port = ip_pool['port']
		ret = str(ip) + ':' + str(port)
		print('获取代理ip成功 -> ', ret)
		return ret
	except Exception as e:
		print('get_ip_pool except:', str(e))
proxies = get_ip_pool() # 调用获取代理ip的函数
requests.get(url=url, headers=headers, proxies={'HTTPS': proxies}) # 发送请求

尽量不要用sleep(1)、sleep(3)这种整数时间的等待，一看就是机器。。
还是那句话，让爬虫程序表现地更像一个人！

time.sleep(random.uniform(0.5, 3)) # 随机等待0.5-3秒

上面4点防爬技术，不一定要全部加入，只看被爬网站是否有防爬技术，多数用到1、2点就搞定

官网：阳光开奖

 经过排查，是通过接口获取数据再由JS来生成这部分网页元素

通过检查元素是有数据的（JS来生成这部分网页元素）

# 抓取双色球历史数据
# 编码：utf-8
import requests
import json
import random
import time
import pandas as pd

data_list = []
num_pages = 1 #抓取多少页数据

# 创建一个DataFrame，用于保存到excel中

for page in range(1, num_pages+1):
 url = 'http://www.cwl.gov.cn/cwl_admin/front/cwlkj/search/kjxx/findDrawNotice?name=ssq&issueCount=&issueStart=&issueEnd=&dayStart=&dayEnd=&pageSize=30&week=&systemType=PC&pageNo='
 url2 = url + str(page)
 # request header，其中最关键的一项，User-Agent，可以写个agent_list，每次请求，随机选择一个agent，像这样：
 agent_list = [
 "Mozilla/5.0 (Linux; U; Android 2.3.6; en-us; Nexus S Build/GRK39F) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
 "Avant Browser/1.2.789rel1 (http://www.avantbrowser.com)",
 "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5",
 "Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.9 (KHTML, like Gecko) Chrome/5.0.310.0 Safari/532.9",
 "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.514.0 Safari/534.7",
 "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/9.0.601.0 Safari/534.14",
 "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/10.0.601.0 Safari/534.14",
 "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.20 (KHTML, like Gecko) Chrome/11.0.672.2 Safari/534.20",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.27 (KHTML, like Gecko) Chrome/12.0.712.0 Safari/534.27",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.24 Safari/535.1",
 "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.120 Safari/535.2",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7",
 "Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre",
 "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.10) Gecko/2009042316 Firefox/3.0.10"
 ]
 headers = {
 'User-Agent': random.choice(agent_list), # 在调用的时候，随机选取一个就可以了
 # 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 Edge/16.16299',
 'Referer': 'http://www.cwl.gov.cn/ygkj/wqkjgg/ssq/',
 'Accept-Encoding': 'gzip, deflate',
 'Accept-Language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7',
 'Connection': 'keep-alive',
 'Upgrade-Insecure-Requests': '1',
 'Cookie': 'HMF_CI=xxxxxxxxxxxxxxxxxxxxxxxxx' # 加入自己的Cookie
 }

 # 使用代理IP
 # proxies = {
 # 'http': 'http://10.10.1.10:3128',
 # 'https': 'http://10.10.1.10:1080',
 # }
 #response = requests.get(url2, headers=headers, proxies=proxies).text

 wbdata = requests.get(url2, headers=headers).text
 time.sleep(random.uniform(0.5, 3)) # 随机等待0.5-3秒
 data = json.loads(wbdata) # json.loads() 方法将 JSON 数组转换为 Python 列表
 news = data['result']

 for n in news:
 df = pd.DataFrame(n)

df.to_excel("双色球历史数据.xlsx")
print('完成')

导出excel

# 抓取双色球历史数据
# 编码：utf-8
import requests
import json
import random
import time
import pandas as pd

data_list = []
# 抓取多少页数据
pageNo = 1
# 页数
pageSize = 30

# 只需要期号、红球、蓝球("code", "red", "blue")三个数据
columns = ["code", "red", "blue"]
df = pd.DataFrame(columns=columns)

for page in range(1, pageNo+1):

 url = 'http://www.cwl.gov.cn/cwl_admin/front/cwlkj/search/kjxx/findDrawNotice?name=ssq&issueCount=&issueStart=&issueEnd=&dayStart=&dayEnd=&pageSize=' + \
 str(pageSize) + '&week=&systemType=PC&pageNo='
 url2 = url + str(page)

 # request header，其中最关键的一项，User-Agent，可以写个agent_list，每次请求，随机选择一个agent，像这样：
 agent_list = [
 "Mozilla/5.0 (Linux; U; Android 2.3.6; en-us; Nexus S Build/GRK39F) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
 "Avant Browser/1.2.789rel1 (http://www.avantbrowser.com)",
 "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5",
 "Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.9 (KHTML, like Gecko) Chrome/5.0.310.0 Safari/532.9",
 "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.514.0 Safari/534.7",
 "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/9.0.601.0 Safari/534.14",
 "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/10.0.601.0 Safari/534.14",
 "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.20 (KHTML, like Gecko) Chrome/11.0.672.2 Safari/534.20",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.27 (KHTML, like Gecko) Chrome/12.0.712.0 Safari/534.27",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.24 Safari/535.1",
 "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.120 Safari/535.2",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7",
 "Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre",
 "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.10) Gecko/2009042316 Firefox/3.0.10"
 ]
 headers = {
 'User-Agent': random.choice(agent_list), # 在调用的时候，随机选取一个就可以了
 # 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 Edge/16.16299',
 'Referer': 'http://www.cwl.gov.cn/ygkj/wqkjgg/ssq/',
 'Accept-Encoding': 'gzip, deflate',
 'Accept-Language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7',
 'Connection': 'keep-alive',
 'Upgrade-Insecure-Requests': '1',
 'Cookie': 'HMF_CI=xxxxxxxxxx' # 加入自己的Cookie
 }

 # 使用代理IP

 wbdata = requests.get(url2, headers=headers).text
 # 随机等待间隔访问 随机等待0.5-3秒
 time.sleep(random.uniform(0.5, 3))
 data = json.loads(wbdata)
 news = data['result']

 # 过滤不要的元素数据
 new_json = json.dumps(
 [{key: x[key] for key in columns} for x in news]
 )
 # 再将JSON 数组转换为 Python 列表list
 new_response = json.loads(new_json)

 for n, arr in enumerate(new_response):
 index = n+(pageNo-1)*pageSize # 插入新数据时要添加索引
 df.loc[index] = arr # 一次插入一行数据

df.to_excel("双色球历史数据2.xlsx")
print('完成')

上面都是获取一个网页的数据，如果源数据网页是有分页的，那如何抓取

# 抓取双色球历史数据
# 编码：utf-8
import requests
import json
import random
import time
import pandas as pd

data_list = []
# 抓取多少页数据
pageNo = 2
# 页数
pageSize = 30

# 只需要期号、红球、蓝球("code", "red", "blue")三个数据
columns = ["code", "red", "blue"]
df = pd.DataFrame(columns=columns)

for page in range(1, pageNo+1):

 url = 'http://www.cwl.gov.cn/cwl_admin/front/cwlkj/search/kjxx/findDrawNotice?name=ssq&issueCount=&issueStart=&issueEnd=&dayStart=&dayEnd=&pageSize=' + \
 str(pageSize) + '&week=&systemType=PC&pageNo='
 url2 = url + str(page)

 # request header，其中最关键的一项，User-Agent，可以写个agent_list，每次请求，随机选择一个agent，像这样：
 agent_list = [
 "Mozilla/5.0 (Linux; U; Android 2.3.6; en-us; Nexus S Build/GRK39F) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
 "Avant Browser/1.2.789rel1 (http://www.avantbrowser.com)",
 "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5",
 "Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.9 (KHTML, like Gecko) Chrome/5.0.310.0 Safari/532.9",
 "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.514.0 Safari/534.7",
 "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/9.0.601.0 Safari/534.14",
 "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/10.0.601.0 Safari/534.14",
 "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.20 (KHTML, like Gecko) Chrome/11.0.672.2 Safari/534.20",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.27 (KHTML, like Gecko) Chrome/12.0.712.0 Safari/534.27",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.24 Safari/535.1",
 "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.120 Safari/535.2",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7",
 "Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre",
 "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.10) Gecko/2009042316 Firefox/3.0.10"
 ]
 headers = {
 'User-Agent': random.choice(agent_list), # 在调用的时候，随机选取一个就可以了
 # 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 Edge/16.16299',
 'Referer': 'http://www.cwl.gov.cn/ygkj/wqkjgg/ssq/',
 'Accept-Encoding': 'gzip, deflate',
 'Accept-Language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7',
 'Connection': 'keep-alive',
 'Upgrade-Insecure-Requests': '1',
 'Cookie': 'xxxxxxxxx' # 加入自己的Cookie
 }

 # 使用代理IP

 wbdata = requests.get(url2, headers=headers).text
 # 随机等待间隔访问 随机等待0.5-3秒
 time.sleep(random.uniform(0.5, 3))
 data = json.loads(wbdata)
 news = data['result']

 # 过滤不要的元素数据
 new_json = json.dumps(
 [{key: x[key] for key in columns} for x in news]
 )
 # 再将JSON 数组转换为 Python 列表list
 new_response = json.loads(new_json)
 # 把抓取每一个网页的数据加入data_list数组中(python中list) extend() 函数用于在列表末尾一次性追加另一个序列中的多个值（用新列表扩展原来的列表） 不能用append()
 data_list.extend(new_response)
 print('------------1.抓取到第' + str(page) + '页数据---------------')

# print(data_list)
for n, arr in enumerate(data_list):
 df.loc[n+1] = arr # 一次插入一行数据
df.to_excel("双色球历史数据.xlsx")
df.head()
print('数据导出导出完成:双色球历史数据.xlsx')

，如果这个编程语言完全不会，用chatgpt来写代码还是有点困难的，对于编程人员来说chatpgt就很好用

参考：

python怎样抓取js生成的页面_ITPUB博客