From 524a5e1e53f7cf65a1abcb154926fa619721351e Mon Sep 17 00:00:00 2001
From: p892kxaor <1987665756@qq.com>
Date: Fri, 25 Nov 2022 20:15:36 +0800
Subject: [PATCH] ADD file via upload

---
 爬虫爬题.py | 92 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 92 insertions(+)
 create mode 100644 爬虫爬题.py

diff --git a/爬虫爬题.py b/爬虫爬题.py
new file mode 100644
index 0000000..abaf855
--- /dev/null
+++ b/爬虫爬题.py
@@ -0,0 +1,92 @@
+import requests
+from bs4 import BeautifulSoup
+from pandas import DataFrame
+import xlwt
+import time
+import re
+
+headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36 Edg/92.0.902.55'}
+
+# 创建 workbook 即新建 excel 文件/工作簿
+workbook = xlwt.Workbook(encoding='utf-8', style_compression=1)
+worksheet = workbook.add_sheet('题', cell_overwrite_ok=True) #创建工作表
+xuhao=1
+worksheet.write(0, 0, "题目")
+worksheet.write(0, 1, "选项+答案")
+for i in range(100,250):
+    url = "https://www.hyluz.cn/search.php?q=单选题：&page={}".format(i)
+    response = requests.get(url=url, headers=headers)
+    html = response.content.decode('utf-8')
+    text = response.text
+    # print(text)
+    dynasties = re.findall(r'<h2><a href="(.*?)" target="_blank"><strong><mark>单选题：</mark></strong>', text, re.DOTALL)
+    for j in dynasties:
+        # print(j)
+        # break
+        response = requests.get(url=j, headers=headers)
+        html = response.content.decode('utf-8')
+        text = response.text
+        # print(text)
+        # break
+        # print(text)
+        # print(html)
+        # soup = BeautifulSoup(html)
+        # print(soup)
+        # position = soup.select('#content >div>div.post > h1> em')
+        # print(position)
+
+
+        dynasties = re.findall(r'<h1>(.*?)</h1>', text, re.DOTALL)
+        print(dynasties)
+        x = re.findall(r'<br>(.*?)</div>', text, re.DOTALL)
+        s = x[0]
+        while("<br><br>" in s):
+            s = s.replace("<br><br>", "<br>")
+        s = s.replace("<br>", ";\t")
+
+        # if "A" in l[5]:
+        #     w="A"
+        # elif "B" in l[5]:
+        #     w="B"
+        # elif "C" in l[5]:
+        #     w="C"
+        # else:
+        #     w="D"
+
+        # option = re.findall(r'<br><br><br><br><br>(.*?)<br><br><br>', text, re.DOTALL)
+        # print(option)
+        # answer=re.findall(r'<br><br><br>(.*?)</div>', text, re.DOTALL)
+        # print(answer)
+        #写入数据
+        worksheet.write(xuhao, 0, dynasties)
+        # worksheet.write(xuhao, 1, l[1])
+        # worksheet.write(xuhao, 2, l[2])
+        # worksheet.write(xuhao, 3, l[3])
+        # worksheet.write(xuhao, 4, l[4])
+        worksheet.write(xuhao, 1, s)
+        xuhao += 1
+    #     break
+    # break
+    time.sleep(1)
+worksheet.col(0).width = 256*100
+worksheet.col(1).width = 256*100
+# worksheet.col(2).width = 256*20
+# worksheet.col(3).width = 256*20
+# worksheet.col(4).width = 256*20
+# worksheet.col(5).width = 256*20
+workbook.save(r'D:\爬虫爬题3.xls')
+
+# for i in name_list:
+#     url = "https://so.gushiwen.cn/mingjus/default.aspx?astr={}".format(i)
+#     response = requests.get(url=url, headers=headers)
+#     html = response.content.decode('utf-8')
+#     text = response.text
+#     dynasties = re.findall(r'<a style=" float:left;" target="_blank" href="/.*?>(.*?)</a>', text, re.DOTALL)
+#     # titles = re.findall(r'<div\sclass="cont">.*?<b>(.*?)</b>', text, re.DOTALL)
+#     for i in range(0, len(dynasties), 2):
+#         print(dynasties[i], dynasties[i + 1])
+#         # 写入数据
+#         worksheet.write(k, 0, dynasties[i])
+#         worksheet.write(k, 1, dynasties[i+1])
+#         k+=1
+