query.py

Add getdata.py

@@ -0,0 +1,95 @@
+import csv
+import requests
+import re, os
+from bs4 import BeautifulSoup
+
+url = ' https://mp.weixin.qq.com/s/K0u_qPFQtWuH4hk5K2xWfQ'
+response = requests.get(url)
+response.encoding = response.apparent_encoding
+response.encoding = 'utf-8'
+html = response.text
+soup = BeautifulSoup(html, 'html.parser')
+ans = soup.select('div.rich_media > div.rich_media_inner ')
+ans1 = ans[0].text.encode()
+
+def openreadtxt(file_name):
+    data = []
+    file = open(file_name, 'r', encoding='utf-8')  # 打开文件
+    file_data = file.readlines()  # 读取所有行
+    for row in file_data:
+        tmp_list = row.split(' ')  # 按‘，’切分每行的数据
+        tmp_list[-1] = tmp_list[-1].replace('\n', '')  # 去掉换行符
+        data.append(tmp_list)  # 将每行数据插入data中
+    file.close()
+    return data
+
+def updateFile(file, old_str, new_str):
+    with open(file, "r", encoding="utf-8") as f1, open("%s.bak" % file, "w", encoding="utf-8") as f2:
+        for line in f1:
+            f2.write(re.sub(old_str, new_str, line))
+    os.remove(file)
+    os.rename("%s.bak" % file, file)
+    f2.close()
+    f1.close()
+
+updateFile(r"test.txt", "；", "。")
+updateFile(r"test.txt", "：", ":")
+updateFile(r"test.txt", "-", "--")
+updateFile(r"test.txt", "确诊病例", "")
+updateFile(r"test.txt", "病例轨迹", "")
+updateFile(r"test.txt", "病例", "&&病例")
+updateFile(r"test.txt", "呼和浩特市应对新型冠状病毒感染", "end")
+data = openreadtxt('test.txt')
+data = str(data)
+result = re.findall("病例\d:.*?(?=&&|end)", data)
+name = []
+date = []
+time = []
+through = []
+Num = 0
+for i in result:
+ NUM = 0
+    f = open('20.txt', 'w', encoding="utf-8")
+    f.write(i)
+    f.close()
+    data = openreadtxt("20.txt")
+    data = str(data)
+    name1 = re.findall("病例\d", data)
+    getOne = re.findall("\d{1,2}月\d{1,2}?日.*?。+(?=\d{1,2}月\d{1,2}日)|\d{1,2}月\d{1,2}?日.*?。+(?=病例)", data)
+    numname = 0
+    for i in getOne:
+     NUM += 1
+        f = open('10.txt', 'w', encoding="utf-8")
+        f.write(i)
+        f.close()
+        data = openreadtxt("10.txt")
+        data = str(data)
+        date1 = re.findall("\d{1,2}月\d{1,2}日+(?=，)", data)[0]
+        date1 = date1.split()
+        time += re.findall("\d{1,2}:\d{1,2}--\d{1,2}:\d{1,2}|\d{1,2}:\d{1,2}", data)
+        updateFile(r"10.txt", "[0-9月\'\",:-]", "")
+        updateFile(r"10.txt", "日，", "。")
+        data = openreadtxt("10.txt")
+        data = str(data)
+        t = re.findall("(?<=。)+.*?。", data)
+        through += t
+        numdate = len(t)
+        Num += numdate
+        numname += numdate
+        x = 0
+        while x < numdate:
+            date += date1
+            x += 1
+    i = 0
+    name2 = name1[0].split()
+    while i < numname:
+        name += name2
+        i += 1
+num = range(0, Num)
+rows = zip(num, name, date, date, time, through)
+with open("test.csv", "w", encoding='utf-8', newline="") as t:
+    writer = csv.writer(t)
+    writer.writerow(["", "病例", "开始日期", "结束日期", "时间", "事件"])
+    for row in rows:
+        writer.writerow(row)
+t.close()

README.md

@@ -1,2 +1,18 @@
-# TDXZ
+import csv
-
+flag=0
+csv_reader=csv.reader(open('test.csv'))
+headers=next(csv_reader)
+case = input("病例名称：")
+Start_date = input("开始日期：")
+End_date = input("结束日期：")
+keyword = input("查询关键字：")
+for row in csv_reader:
+    if case in row[0]:
+        if Start_date==row[1]:
+            if End_date==row[2]:
+                if keyword in row[4]:
+                    row=' '.join(row)
+                    print(row)
+                    flag=1
+if flag==0:
+    print("未查找到！")

Untitled.md

@@ -0,0 +1,97 @@
+```python
+import csv
+import requests
+import re, os
+from bs4 import BeautifulSoup
+
+url = ' https://mp.weixin.qq.com/s/K0u_qPFQtWuH4hk5K2xWfQ'
+response = requests.get(url)
+response.encoding = response.apparent_encoding
+response.encoding = 'utf-8'
+html = response.text
+soup = BeautifulSoup(html, 'html.parser')
+ans = soup.select('div.rich_media > div.rich_media_inner ')
+ans1 = ans[0].text.encode()
+
+def openreadtxt(file_name):
+    data = []
+    file = open(file_name, 'r', encoding='utf-8')  # 打开文件
+    file_data = file.readlines()  # 读取所有行
+    for row in file_data:
+        tmp_list = row.split(' ')  # 按‘，’切分每行的数据
+        tmp_list[-1] = tmp_list[-1].replace('\n', '')  # 去掉换行符
+        data.append(tmp_list)  # 将每行数据插入data中
+    file.close()
+    return data
+
+  def updateFile(file, old_str, new_str):
+    with open(file, "r", encoding="utf-8") as f1, open("%s.bak" % file, "w", encoding="utf-8") as f2:
+        for line in f1:
+            f2.write(re.sub(old_str, new_str, line))
+    os.remove(file)
+    os.rename("%s.bak" % file, file)
+    f2.close()
+    f1.close()
+
+   updateFile(r"test.txt", "；", "。")
+updateFile(r"test.txt", "：", ":")
+updateFile(r"test.txt", "-", "--")
+updateFile(r"test.txt", "确诊病例", "")
+updateFile(r"test.txt", "病例轨迹", "")
+updateFile(r"test.txt", "病例", "&&病例")
+updateFile(r"test.txt", "呼和浩特市应对新型冠状病毒感染", "end")
+data = openreadtxt('test.txt')
+data = str(data)
+result = re.findall("病例\d:.*?(?=&&|end)", data)
+name = []
+date = []
+time = []
+through = []
+Num = 0
+for i in result:
+    NUM = 0
+    f = open('20.txt', 'w', encoding="utf-8")
+    f.write(i)
+    f.close()
+    data = openreadtxt("20.txt")
+    data = str(data)
+    name1 = re.findall("病例\d", data)
+    getOne = re.findall("\d{1,2}月\d{1,2}?日.*?。+(?=\d{1,2}月\d{1,2}日)|\d{1,2}月\d{1,2}?日.*?。+(?=病例)", data)
+    numname = 0
+    for i in getOne:
+        NUM += 1
+        f = open('10.txt', 'w', encoding="utf-8")
+        f.write(i)
+        f.close()
+        data = openreadtxt("10.txt")
+        data = str(data)
+        date1 = re.findall("\d{1,2}月\d{1,2}日+(?=，)", data)[0]
+        date1 = date1.split()
+        time += re.findall("\d{1,2}:\d{1,2}--\d{1,2}:\d{1,2}|\d{1,2}:\d{1,2}", data)
+        updateFile(r"10.txt", "[0-9月\'\",:-]", "")
+        updateFile(r"10.txt", "日，", "。")
+        data = openreadtxt("10.txt")
+        data = str(data)
+        t = re.findall("(?<=。)+.*?。", data)
+        through += t
+        numdate = len(t)
+        Num += numdate
+        numname += numdate
+        x = 0
+        while x < numdate:
+                date += date1
+            x += 1
+    i = 0
+    name2 = name1[0].split()
+    while i < numname:
+        name += name2
+        i += 1
+num = range(0, Num)
+rows = zip(num, name, date, date, time, through)
+with open("test.csv", "w", encoding='utf-8', newline="") as t:
+    writer = csv.writer(t)
+    writer.writerow(["", "病例", "开始日期", "结束日期", "时间", "事件"])
+    for row in rows:
+        writer.writerow(row)
+t.close()
+```

Untitled1.7.md

@@ -0,0 +1,125 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "63b3eaa5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import csv\n",
+    "import requests\n",
+    "import re, os\n",
+    "from bs4 import BeautifulSoup\n",
+    "\n",
+    "url = ' https://mp.weixin.qq.com/s/K0u_qPFQtWuH4hk5K2xWfQ'\n",
+    "response = requests.get(url)\n",
+    "response.encoding = response.apparent_encoding\n",
+    "response.encoding = 'utf-8'\n",
+    "html = response.text\n",
+    "soup = BeautifulSoup(html, 'html.parser')\n",
+    "ans = soup.select('div.rich_media > div.rich_media_inner ')\n",
+    "ans1 = ans[0].text.encode()\n",
+    "\n",
+    "def openreadtxt(file_name):\n",
+    "    data = []\n",
+    "    file = open(file_name, 'r', encoding='utf-8') \n",
+    "    file_data = file.readlines()  \n",
+    "    for row in file_data:\n",
+    "        tmp_list = row.split(' ')\n",
+    "        tmp_list[-1] = tmp_list[-1].replace('\\n', '')\n",
+    "        data.append(tmp_list)\n",
+    "    file.close()\n",
+    "    return data\n",
+    "\n",
+    "def updateFile(file, old_str, new_str):\n",
+    "    with open(file, \"r\", encoding=\"utf-8\") as f1, open(\"%s.bak\" % file, \"w\", encoding=\"utf-8\") as f2:\n",
+    "        for line in f1:\n",
+    "            f2.write(re.sub(old_str, new_str, line))\n",
+    "    os.remove(file)\n",
+    "    f2.close()\n",
+    "    f1.close()\n",
+    "\n",
+    "updateFile(r\"test.txt\", \"；\", \"。\")\n",
+    "updateFile(r\"test.txt\", \"：\", \":\")\n",
+    "updateFile(r\"test.txt\", \"-\", \"--\")\n",
+    "updateFile(r\"test.txt\", \"确诊病例\", \"\")\n",
+    "updateFile(r\"test.txt\", \"病例轨迹\", \"\")\n",
+    "updateFile(r\"test.txt\", \"病例\", \"&&病例\")\n",
+    "updateFile(r\"test.txt\", \"呼和浩特市应对新型冠状病毒感染\", \"end\")\n",
+    "data = openreadtxt('test.txt')\n",
+    "data = str(data)\n",
+    "result = re.findall(\"病例\\d:.*?(?=&&|end)\", data)\n",
+    "name = []\n",
+    "date = []\n",
+    "time = []\n",
+    "through = []\n",
+    "Num = 0\n",
+    "for i in result:\n",
+    "    NUM = 0\n",
+    "    f = open('20.txt', 'w', encoding=\"utf-8\")\n",
+    "    f.write(i)\n",
+    "    f.close()\n",
+    "    data = openreadtxt(\"20.txt\")\n",
+    "    data = str(data)\n",
+    "    name1 = re.findall(\"病例\\d\", data)\n",
+    "    getOne = re.findall(\"\\d{1,2}月\\d{1,2}?日.*?。+(?=\\d{1,2}月\\d{1,2}日)|\\d{1,2}月\\d{1,2}?日.*?。+(?=病例)\", data)\n",
+    "    numname = 0\n",
+    "    for i in getOne:\n",
+    "        NUM += 1\n",
+    "        f = open('10.txt', 'w', encoding=\"utf-8\")\n",
+    "        f.write(i)\n",
+    "        f.close()\n",
+    "        data = openreadtxt(\"10.txt\")\n",
+    "        data = str(data)\n",
+    "        date1 = re.findall(\"\\d{1,2}月\\d{1,2}日+(?=，)\", data)[0]\n",
+    "        date1 = date1.split()\n",
+    "        time += re.findall(\"\\d{1,2}:\\d{1,2}--\\d{1,2}:\\d{1,2}|\\d{1,2}:\\d{1,2}\", data)\n",
+    "        updateFile(r\"10.txt\", \"[0-9月\\'\\\",:-]\", \"\")\n",
+    "        updateFile(r\"10.txt\", \"日，\", \"。\")\n",
+    "        data = openreadtxt(\"10.txt\")\n",
+    "        data = str(data)\n",
+    "        t = re.findall(\"(?<=。)+.*?。\", data)\n",
+    "        through += t\n",
+    "        numdate = len(t)\n",
+    "        Num += numdate\n",
+    "        numname += numdate\n",
+    "        x = 0\n",
+    "        while x < numdate:\n",
+    "                date += date1\n",
+    "            x += 1\n",
+    "    i = 0\n",
+    "    name2 = name1[0].split()\n",
+    "    while i < numname:\n",
+    "        name += name2\n",
+    "        i += 1\n",
+    "num = range(0, Num)\n",
+    "rows = zip(num, name, date, date, time, through)\n",
+    "with open(\"test.csv\", \"w\", encoding='utf-8', newline=\"\") as t:\n",
+    "    writer = csv.writer(t)\n",
+    "    writer.writerow([\"\", \"病例\", \"开始日期\", \"结束日期\", \"时间\", \"事件\"])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Untitled17.ipynb

@@ -0,0 +1,126 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "63b3eaa5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import csv\n",
+    "import requests\n",
+    "import re, os\n",
+    "from bs4 import BeautifulSoup\n",
+    "\n",
+    "url = ' https://mp.weixin.qq.com/s/K0u_qPFQtWuH4hk5K2xWfQ'\n",
+    "response = requests.get(url)\n",
+    "response.encoding = response.apparent_encoding\n",
+    "response.encoding = 'utf-8'\n",
+    "html = response.text\n",
+    "soup = BeautifulSoup(html, 'html.parser')\n",
+    "ans = soup.select('div.rich_media > div.rich_media_inner ')\n",
+    "ans1 = ans[0].text.encode()\n",
+    "\n",
+    "def openreadtxt(file_name):\n",
+    "    data = []\n",
+    "    file = open(file_name, 'r', encoding='utf-8') \n",
+    "    file_data = file.readlines()  \n",
+    "    for row in file_data:\n",
+    "        tmp_list = row.split(' ')\n",
+    "        tmp_list[-1] = tmp_list[-1].replace('\\n', '')\n",
+    "        data.append(tmp_list)\n",
+    "    file.close()\n",
+    "    return data\n",
+    "\n",
+    "  def updateFile(file, old_str, new_str):\n",
+    "    with open(file, \"r\", encoding=\"utf-8\") as f1, open(\"%s.bak\" % file, \"w\", encoding=\"utf-8\") as f2:\n",
+    "        for line in f1:\n",
+    "            f2.write(re.sub(old_str, new_str, line))\n",
+    "    os.remove(file)\n",
+    "    os.rename(\"%s.bak\" % file, file)\n",
+    "    f2.close()\n",
+    "    f1.close()\n",
+    "\n",
+    "updateFile(r\"test.txt\", \"；\", \"。\")\n",
+    "updateFile(r\"test.txt\", \"：\", \":\")\n",
+    "updateFile(r\"test.txt\", \"-\", \"--\")\n",
+    "updateFile(r\"test.txt\", \"确诊病例\", \"\")\n",
+    "updateFile(r\"test.txt\", \"病例轨迹\", \"\")\n",
+    "updateFile(r\"test.txt\", \"病例\", \"&&病例\")\n",
+    "updateFile(r\"test.txt\", \"呼和浩特市应对新型冠状病毒感染\", \"end\")\n",
+    "data = openreadtxt('test.txt')\n",
+    "data = str(data)\n",
+    "result = re.findall(\"病例\\d:.*?(?=&&|end)\", data)\n",
+    "name = []\n",
+    "date = []\n",
+    "time = []\n",
+    "through = []\n",
+    "Num = 0\n",
+    "for i in result:\n",
+    "    NUM = 0\n",
+    "    f = open('20.txt', 'w', encoding=\"utf-8\")\n",
+    "    f.write(i)\n",
+    "    f.close()\n",
+    "    data = openreadtxt(\"20.txt\")\n",
+    "    data = str(data)\n",
+    "    name1 = re.findall(\"病例\\d\", data)\n",
+    "    getOne = re.findall(\"\\d{1,2}月\\d{1,2}?日.*?。+(?=\\d{1,2}月\\d{1,2}日)|\\d{1,2}月\\d{1,2}?日.*?。+(?=病例)\", data)\n",
+    "    numname = 0\n",
+    "    for i in getOne:\n",
+    "        NUM += 1\n",
+    "        f = open('10.txt', 'w', encoding=\"utf-8\")\n",
+    "        f.write(i)\n",
+    "        f.close()\n",
+    "        data = openreadtxt(\"10.txt\")\n",
+    "        data = str(data)\n",
+    "        date1 = re.findall(\"\\d{1,2}月\\d{1,2}日+(?=，)\", data)[0]\n",
+    "        date1 = date1.split()\n",
+    "        time += re.findall(\"\\d{1,2}:\\d{1,2}--\\d{1,2}:\\d{1,2}|\\d{1,2}:\\d{1,2}\", data)\n",
+    "        updateFile(r\"10.txt\", \"[0-9月\\'\\\",:-]\", \"\")\n",
+    "        updateFile(r\"10.txt\", \"日，\", \"。\")\n",
+    "        data = openreadtxt(\"10.txt\")\n",
+    "        data = str(data)\n",
+    "        t = re.findall(\"(?<=。)+.*?。\", data)\n",
+    "        through += t\n",
+    "        numdate = len(t)\n",
+    "        Num += numdate\n",
+    "        numname += numdate\n",
+    "        x = 0\n",
+    "        while x < numdate:\n",
+    "                date += date1\n",
+    "            x += 1\n",
+    "    i = 0\n",
+    "    name2 = name1[0].split()\n",
+    "    while i < numname:\n",
+    "        name += name2\n",
+    "        i += 1\n",
+    "num = range(0, Num)\n",
+    "rows = zip(num, name, date, date, time, through)\n",
+    "with open(\"test.csv\", \"w\", encoding='utf-8', newline=\"\") as t:\n",
+    "    writer = csv.writer(t)\n",
+    "    writer.writerow([\"\", \"病例\", \"开始日期\", \"结束日期\", \"时间\", \"事件\"])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Untitled17.md

@@ -0,0 +1,94 @@
+```python
+import csv
+import requests
+import re, os
+from bs4 import BeautifulSoup
+
+url = ' https://mp.weixin.qq.com/s/K0u_qPFQtWuH4hk5K2xWfQ'
+response = requests.get(url)
+response.encoding = response.apparent_encoding
+response.encoding = 'utf-8'
+html = response.text
+soup = BeautifulSoup(html, 'html.parser')
+ans = soup.select('div.rich_media > div.rich_media_inner ')
+ans1 = ans[0].text.encode()
+
+def openreadtxt(file_name):
+    data = []
+    file = open(file_name, 'r', encoding='utf-8') 
+    file_data = file.readlines()  
+    for row in file_data:
+        tmp_list = row.split(' ')
+        tmp_list[-1] = tmp_list[-1].replace('\n', '')
+        data.append(tmp_list)
+    file.close()
+    return data
+
+  def updateFile(file, old_str, new_str):
+    with open(file, "r", encoding="utf-8") as f1, open("%s.bak" % file, "w", encoding="utf-8") as f2:
+        for line in f1:
+            f2.write(re.sub(old_str, new_str, line))
+    os.remove(file)
+    os.rename("%s.bak" % file, file)
+    f2.close()
+    f1.close()
+
+updateFile(r"test.txt", "；", "。")
+updateFile(r"test.txt", "：", ":")
+updateFile(r"test.txt", "-", "--")
+updateFile(r"test.txt", "确诊病例", "")
+updateFile(r"test.txt", "病例轨迹", "")
+updateFile(r"test.txt", "病例", "&&病例")
+updateFile(r"test.txt", "呼和浩特市应对新型冠状病毒感染", "end")
+data = openreadtxt('test.txt')
+data = str(data)
+result = re.findall("病例\d:.*?(?=&&|end)", data)
+name = []
+date = []
+time = []
+through = []
+Num = 0
+for i in result:
+    NUM = 0
+    f = open('20.txt', 'w', encoding="utf-8")
+    f.write(i)
+    f.close()
+    data = openreadtxt("20.txt")
+    data = str(data)
+    name1 = re.findall("病例\d", data)
+    getOne = re.findall("\d{1,2}月\d{1,2}?日.*?。+(?=\d{1,2}月\d{1,2}日)|\d{1,2}月\d{1,2}?日.*?。+(?=病例)", data)
+    numname = 0
+    for i in getOne:
+        NUM += 1
+        f = open('10.txt', 'w', encoding="utf-8")
+        f.write(i)
+        f.close()
+        data = openreadtxt("10.txt")
+        data = str(data)
+        date1 = re.findall("\d{1,2}月\d{1,2}日+(?=，)", data)[0]
+        date1 = date1.split()
+        time += re.findall("\d{1,2}:\d{1,2}--\d{1,2}:\d{1,2}|\d{1,2}:\d{1,2}", data)
+        updateFile(r"10.txt", "[0-9月\'\",:-]", "")
+        updateFile(r"10.txt", "日，", "。")
+        data = openreadtxt("10.txt")
+        data = str(data)
+        t = re.findall("(?<=。)+.*?。", data)
+        through += t
+        numdate = len(t)
+        Num += numdate
+        numname += numdate
+        x = 0
+        while x < numdate:
+                date += date1
+            x += 1
+    i = 0
+    name2 = name1[0].split()
+    while i < numname:
+        name += name2
+        i += 1
+num = range(0, Num)
+rows = zip(num, name, date, date, time, through)
+with open("test.csv", "w", encoding='utf-8', newline="") as t:
+    writer = csv.writer(t)
+    writer.writerow(["", "病例", "开始日期", "结束日期", "时间", "事件"])
+```

query.py Add query.py

@@ -0,0 +1,24 @@
+# -*- coding: gbk -*-
+import csv
+import re
+
+case = input("请输入:")
+Start_date = input("要查询的开始时间:")
+End_date = input("要查询的结束时间:")
+keyword = input("关键字:")
+with open('test.csv', 'r', encoding='utf-8') as f:
+    cs = list(csv.reader(f))
+    for i in cs:
+        name = str(i[1])
+        Bdate = str(i[2])
+        Edate = str(i[3])
+        Time = str(i[4])
+        thought = str(i[5])
+        if case == name or case == "  ":
+            if Start_date == Bdate or Start_date == "  ":
+                if End_date == Edate or End_date == "  ":
+                    s = re.findall(keyword, thought)
+                    if keyword == "  " :
+                        print(name + "  " + Bdate + Time + thought)
+                    elif  s!=[]:
+                        print(name+"  "+Bdate+Time+thought)