1、準備要爬取企業名稱數據表

企業名稱
紹興市袍江王新國家庭農場
紹興市鄭杜糧油專業合作社
紹興市越城區興華家庭農場
紹興市越城區銳意家庭農場
紹興市越城區青甸畈家庭農場
紹興市袍江王新國家庭農場
紹興市袍江月明家庭農場
紹興市越城區夏景權鮮果園
紹興市越城區匡群家庭農場
紹興市袍江趙成興家庭農場
紹興市越城區真香果園
紹興市越城區聚客來家庭農場
紹興市越城區果真不錯果園
紹興市越城區亮豐家庭農場
紹興縣富盛鎮北山糧油專業合作社
紹興市袍江銀軍家庭農場
紹興市袍江仲康家庭農場
紹興市越城區娜家果園
紹興市越城區建峰家庭農場
紹興市越城區國信家庭農場

2、爬取代碼

import time
import requests
from bs4 import BeautifulSoup
import re
import json
import pandas as pd
import jsonpath
from datetime import datetime
import random
from urllib3.exceptions import ConnectTimeoutError# 初始化會話和請求頭
session = requests.Session()url = "https://www.qcc.com/web/search?"header = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36 Edg/135.0.0.0","accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7","accept-encoding": "gzip, deflate, br, zstd","accept-language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6","cookie": ""  #填寫自己cookie}proxy_url = 'http://api.89ip.cn/tqdl.html?api=1&num=60&port=&address=%E5%B9%BF%E4%B8%9C%E7%9C%81&isp='
test_url = 'http://httpbin.org/ip'  # 用于測試代理是否有效的地址valid_proxies = []
# 獲取有效代理池和構造代理字典
def get_valid_proxies():try:resp = requests.get(proxy_url, timeout=10)resp.raise_for_status()proxy_ips = re.findall(r'\d+\.\d+\.\d+\.\d+:\d+', resp.text)for ip in proxy_ips:proxy = {'http': f'http://{ip}', 'https': f'http://{ip}'}try:# 測試代理是否有效（設置短超時快速篩選）test_resp = requests.get(test_url, proxies=proxy, timeout=5)if test_resp.status_code == 200:valid_proxies.append(proxy)# 構造代理字典print( {'http': f'http://{ip}','https': f'http://{ip}'})except (requests.exceptions.ProxyError, ConnectTimeoutError, requests.exceptions.Timeout):#print(f"無效代理: {ip}")continuereturn valid_proxiesexcept Exception as e:print(f"獲取代理失敗: {e}")return None# 測試獲取有效代理池
#get_valid_proxies()
#隨機選擇一個有效代理IP
def get_proxy():"""獲取代理"""try:# 隨機選擇一個代理ip_port = random.choice(get_valid_proxies())print("選擇的代理IP:", ip_port)except Exception as e:print(f"獲取代理失敗: {e}")return None# 初始化數據存儲列表（放在循環外部）
company_data = []
# 讀取Excel文件
red_execl= pd.read_excel(r"C:\Users\zzx\Desktop\浙江_紹興_1.xlsx")company_names = red_execl.iloc[:,0].tolist()
#print(company_names)def safe_jsonpath(data, path, default="",strict_type=False):"""安全解析 JSONPath，返回第一個匹配值或默認值- 自動處理 None、空列表、類型不匹配- 根據 default 參數類型自動轉換返回值類型"""result = jsonpath.jsonpath(data, path)# 處理無效路徑或非列表結果if not isinstance(result,list) or len(result) == 0:return defaultvalue = result[0]# 處理空值和類型轉換if value is None:return default# 類型處理邏輯if strict_type:if isinstance(value, type(default)):return valuereturn defaulttry:return type(default)(value)  # 根據 default 的類型轉換結果except (TypeError, ValueError,):return default
TAG_LIST = ["高新技術企業", "科技型中小企業", "專精特新小巨人企業","專精特新中小企業", "創新型中小企業", "制造業單項冠軍企業","制造業單項冠軍產品企業", "獨角獸企業", "瞪羚企業", "企業技術中心","重點實驗室", "技術創新示范企業", "技術先進型服務企業","眾創空間", "隱形冠軍企業"
]
def parse_tags(data):"""解析企業標簽"""tags_info = safe_jsonpath(data, "$..TagsInfoV2", default=[])return { f"是否{tag}":  "是" if any(t.get('Name') ==  tag for t in tags_info)  else "否" for tag in TAG_LIST }def process_company_data(name):"""處理單個公司數據"""max_retries = 3for attempt in range(max_retries):try:proxies = get_proxy()'''proxies = {'http': 'http://120.24.73.25:8181','https': 'http://120.24.73.25:8181'}'''params = {"key": name}response = session.get(url,headers=header,params=params,proxies=proxies,timeout=10)#print(response.json())if response.status_code != 200:raise Exception(f"狀態碼: {response.status_code}")if "驗證碼" in response.text:raise Exception("觸發反爬驗證碼")# 用BeautifulSoup提取所有<script>標簽soup = BeautifulSoup(response.text, 'html.parser')#print(soup)scripts = soup.find_all('script')#print(scripts)# 正則匹配目標變量（例如window.__INITIAL_STATE__）pattern = re.compile(r'window\.__INITIAL_STATE__\s*=\s*({.*?});', re.DOTALL)for script in soup.find_all('script'):if script.string and (match := pattern.search(script.string)):data = json.loads(match.group(1))#print(data)#國標行業--碼值credit_code = safe_jsonpath(data, "$..CreditCode", default="")#org_code = ""#if len(credit_code) >= 10:  # 確保可以安全切片org_code = f"{credit_code[8:-2]}-{credit_code[-2]}"if credit_code else ""#成立日期處理start_date = safe_jsonpath(data, "$..StartDate",default=0)#formatted_date = ""#if isinstance(start_date, (int, float)) and start_date > 0:formatted_date = datetime.fromtimestamp(start_date / 1000).strftime("%Y-%m-%d")if start_date else ""#營業期限allottedSpan = safe_jsonpath(data, "$..allottedSpan",default=0)formatted_allottedSpan =  datetime.fromtimestamp(allottedSpan / 1000).strftime("%Y-%m-%d")if allottedSpan else ""company_info = {"企業名稱": re.sub(r'<[^>]+>', '', safe_jsonpath(data, "$..Name", default="")),"法定代表人": safe_jsonpath(data, "$..OperName", default=""),"登記狀態": safe_jsonpath(data, "$..ShortStatus", default=""),"成立日期": formatted_date,"注冊資本": safe_jsonpath(data, "$..RegistCapi", default=""),# "實繳資本":jsonpath.jsonpath(data,"$..RegistCapi")[0],# "人員":jsonpath.jsonpath(data,"$..companyScale")[0],"國標行業--碼值": safe_jsonpath(data, "$..IndustryCode", default="") + safe_jsonpath(data, "$..SmallCategoryCode", default=""),"國標行業--中文": safe_jsonpath(data, "$..SmallCategory", default=""),"統一社會信用代碼": safe_jsonpath(data, "$..CreditCode", default=""),"組織機構代碼": org_code,"登記號": safe_jsonpath(data, "$..No", default=""),"納稅人識別號": safe_jsonpath(data, "$..CreditCode", default=""),#"納稅人資質": "一般納稅人","核準日期": safe_jsonpath(data, "$..CheckDate",default=""),"登記機關": safe_jsonpath(data, "$..City", default="") + safe_jsonpath(data, "$..County",default="") + "市場監督管理局","企業類型": safe_jsonpath(data, "$..EconKind", default=""),#"營業期限": formatted_allottedSpan ,"所屬地區": safe_jsonpath(data, "$..Province", default="") + safe_jsonpath(data, "$..City",default="") + safe_jsonpath(data, "$..County", default=""),# "英文名": jsonpath.jsonpath(data, "$..EnglishName")[0],# "經營范圍": jsonpath.jsonpath(data, "$..Scope")[0],"電話": safe_jsonpath(data, "$..ContactNumber", default=0),"注冊地址": safe_jsonpath(data, "$..Address", default=""),"官網": safe_jsonpath(data, "$..GW", default=""),"郵箱": safe_jsonpath(data, "$..Email", default=""),"企業規模": safe_jsonpath(data, "$..Scale", default="")}print(company_info)#合并標簽信息return {**company_info,**parse_tags(data)}breakexcept Exception as e:print(f"嘗試 {attempt + 1}/{max_retries} 失敗: {e}")time.sleep(10)return NoneBATCH_SIZE = 10  #
# 主處理循環
for index, name in enumerate(company_names):print(f"處理第 {index + 1} 家公司: {name}")# 獲取公司數據info = process_company_data(name)if info:company_data.append(info)else:print(f"警告：{name} 數據為空")# 每處理10個公司保存一次if (index+1) % BATCH_SIZE == 0:pd.DataFrame(company_data).to_excel("temp_result.xlsx", index=False)# 隨機延遲time.sleep(30 + random.randint(5, 15))
if company_data:df = pd.DataFrame(company_data)df.to_excel(r"C:\Users\zzx\Desktop\company_data.xlsx",index=False)print("數據添加成功")
else:print("所有公司數據獲取失敗")

3、查看效果