Add getdata.py

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()