From 117aa4abbc469bc2e9793a67f25749f490571d7e Mon Sep 17 00:00:00 2001
From: pzqw7kh8u <1403016661@qq.com>
Date: Sat, 23 Apr 2022 11:16:48 +0800
Subject: [PATCH] ADD file via upload

---
 getdata.py | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)
 create mode 100644 getdata.py

diff --git a/getdata.py b/getdata.py
new file mode 100644
index 0000000..eb2cf1c
--- /dev/null
+++ b/getdata.py
@@ -0,0 +1,35 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[ ]:
+
+
+import requests
+import  bs4
+import pandas as pd
+result = {"jobname": [],   # 病例名称
+          "area": [],  # 开始日期
+          "salary": [],  # 结束日期
+          "url": [],   # 时间
+            "edu":[]  #事件
+          }
+for i in range(11):
+    url = " https://mp.weixin.qq.com/s/K0u_qPFQtWuH4hk5K2xWfQ " + str(i)
+    print(url)
+    r = requests.get(url)
+    html = bs4.BeautifulSoup(r.text, "html.parser")
+    all_job = html.find("ul", class_="sojob-list").find_all("li")
+    for date in all_job:
+        name = date.find("a", target="_blank").text.strip()
+        area = date.find("a", class_="area").text
+        salary = date.find("span", class_="text-warning").text
+        url = date.find("a", class_="area")["href"]
+        edu = date.find("span", class_="edu").text
+        result["jobname"].append(name)
+        result["area"].append(area)
+        result["salary"].append(salary)
+        result["url"].append(url)
+        result["edu"].append(edu)
+    df = pd.DataFrame(result)
+    df.to_csv("shenzhen_Zhaopin.csv", encoding="utf_8_sig")
+