From b5088a556d0efa001c44f6f3d76068d5cdabd19e Mon Sep 17 00:00:00 2001
From: p3gsryuwh <2841528154@qq.com>
Date: Thu, 27 Apr 2023 23:46:45 +0800
Subject: [PATCH] ADD file via upload

---
 爬取数据.py | 70 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 70 insertions(+)
 create mode 100644 爬取数据.py

diff --git a/爬取数据.py b/爬取数据.py
new file mode 100644
index 0000000..a52d8c0
--- /dev/null
+++ b/爬取数据.py
@@ -0,0 +1,70 @@
+from selenium import webdriver
+import time
+from selenium.webdriver.common.by import By
+from lxml.html import etree
+import csv
+
+all_data = []  # 保存全部数据
+url = "https://we.51job.com/pc/search?keyword=python&searchType=2&sortType=0&metro="
+
+option = webdriver.ChromeOptions()
+
+driver = webdriver.Chrome(options=option)
+
+driver.get(url)
+time.sleep(1)  # 等待网页加载
+error_page = []
+
+def get_info(text):
+    doc = etree.HTML(text)
+    job_list = doc.xpath('//div[@class="j_joblist"]/div')  # 定位到职位列表
+    data = []
+    for job in job_list:
+        try:
+            job_dict = {}
+            job_dict['招聘时间'] = job.xpath('./a/div/span[@class="time"]/text()')[0]
+            job_dict['职位名称'] = job.xpath('./a/div/span[@class="jname at"]/text()')[0]
+            job_dict['详情链接'] = job.xpath('./a/@href')[0]
+            job_dict['公司名称'] = job.xpath('./div[@class="er"]/a/text()')[0]
+            job_dict['所属行业'] = job.xpath('./div[@class="er"]/p[@class="int at"]/text()')[0]
+            Type_num = job.xpath('./div[@class="er"]/p[@class="dc at"]/text()')[0]
+            job_dict['企业性质'] = Type_num.split('|')[0].replace(' ', '')
+            job_dict['公司人数'] = Type_num.split('|')[-1].replace(' ', '')
+            job_dict['职位关键词'] = ' '.join(job.xpath('./a/p[@class="tags"]//text()'))
+            job_dict['工资'] = job.xpath('./a/p/span[@class="sal"]/text()')[0]
+            job_dict['公司地址'] = job.xpath('./a/p/span[@class="d at"]/span[1]/text()')[0]
+            job_dict['工作经验'] = job.xpath('./a/p/span[@class="d at"]/span[3]/text()')[0]
+            a = job.xpath('./a/p/span[@class="d at"]//span/text()')
+            job_dict['公司地址'] = a[0]
+            job_dict['工作经验'] = a[2]
+            job_dict['学历'] = a[-1]
+            data.append(job_dict)
+        except:
+            pass
+    return data
+
+
+for i in range(50):  # 爬取40页
+    try:
+        print(f"正在爬取第{i + 1}页的数据")
+
+        html = driver.page_source  # 获取网页源码
+        all_data.extend(get_info(html))  # 解析网页源码
+        # 下一页按钮
+        next_btn = driver.find_element(By.XPATH, '//button[@class="btn-next"]')
+        next_btn.click()  # 点击下一页
+        time.sleep(1)  # 等待网页加载
+    except:
+        pass
+
+def job_save(data):  # csv模块保存数据
+    headers = ['招聘时间', '职位名称', '详情链接', '公司名称', '所属行业', '企业性质', "职位关键词", '工资', '公司地址', '学历', '工作经验', '公司人数']
+    with open('python.csv', 'w', encoding='utf-8-sig', newline='') as fp:
+        dict_witer = csv.DictWriter(fp, headers)
+        dict_witer.writeheader()
+        dict_witer.writerows(data)
+        print('数据保存成功!!!')
+        print('-' * 50)
+
+driver.close()
+job_save(all_data)  # 保存数据