新增一个网站的爬取

junit/test_main.py

@@ -0,0 +1,59 @@
+import random
+import time
+
+from curl_cffi import requests
+import csv
+
+page = 1
+size = 10
+
+
+def get_data(page, size=100):
+	# 目标 URL
+	url = f"https://service.scctc.org.cn/ucenter/api/certificate/pageList?current={page}&size={size}&certificateCategory=1"
+
+	headers = {
+		"host": "service.scctc.org.cn",
+		"user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36"
+	}
+
+	# 发送 GET 请求获取 JSON 数据
+	response = requests.get(url, headers=headers)
+	print(response.text)
+	return response.json()  # 将响应转换为 JSON 格式
+
+
+def save_data(all_records):
+	file_name = "/Users/renmeng/Downloads/scctc.csv"
+	if all_records:
+		csv_columns = all_records[0].keys()  # 获取列标题
+
+		# 导出到 CSV 文件
+		with open(file_name, mode='w', newline='', encoding='utf-8') as file:
+			writer = csv.DictWriter(file, fieldnames=csv_columns)
+			writer.writeheader()  # 写入列标题
+			writer.writerows(all_records)  # 写入所有记录
+
+		print("All data exported to all_records.csv successfully.")
+	else:
+		print("No data to export.")
+
+
+all_records = []
+try:
+	data = get_data(page)
+	pages = data["data"]["pages"]
+	print(pages)
+	for i in range(page + 1, pages + 1):
+		print(f"开始抓取第 [{i}] 业页数据")
+		data = get_data(i)
+		records = data["data"]["records"]
+		all_records.extend(records)
+		sleep_time = random.randint(2, 10)
+		print(f"程序需要休息一下。休息时间是：{sleep_time}s")
+		time.sleep(sleep_time)
+	print("抓取完毕，开始生成csv文件！")
+except Exception as e:
+	print(f"程序异常退出！{e}")
+finally:
+	save_data(all_records)