From 19b0cef7c75cbb80e1cf0d514f9d70caf79134f6 Mon Sep 17 00:00:00 2001
From: hnu202109070126 <hnu202109070126@qq.com>
Date: Wed, 1 Jun 2022 16:16:29 +0800
Subject: [PATCH] ADD file via upload

---
 大作业-爬虫.py | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)
 create mode 100644 大作业-爬虫.py

diff --git a/大作业-爬虫.py b/大作业-爬虫.py
new file mode 100644
index 0000000..3d74a0e
--- /dev/null
+++ b/大作业-爬虫.py
@@ -0,0 +1,30 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Sun May 15 20:46:07 2022
+
+@author: 张景瑞
+"""
+import requests
+import re
+headers={
+    "user-agent":'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.54 Safari/537.36 Edg/101.0.1210.39'
+    }#请求头信息
+message=[]
+for page in range(10):
+    if page==0:
+        url="https://top.chinaz.com/gongsi/index_zhuce.html"
+    else:
+        url="https://top.chinaz.com/gongsi/index_zhuce_{}.html".format(page + 1)
+    response=requests.get(url, headers=headers)
+    html=response.text
+    name=re.findall('<a.*?target="_blank">(.+?)</a></h3>', html)
+    fund=re.findall('注册资本：</span>(.*?)</p>', html)
+    pack=list(zip(name,fund))
+    message.extend(pack)#写入列表
+import csv
+with open("content.csv", "w") as f:
+    w=csv.writer(f)
+    w.writerows(message)
+import pandas as pd
+df = pd.read_csv("content.csv", names=["name", "fund"],encoding='gb2312')
+print(df.head(20))