pandas で html の table の読み書き

html ファイルの作成

html_create.py

#! /usr/bin/python
# -*- coding: utf-8 -*-
#
#   html_create.py
#
#                   Oct/01/2018
# ------------------------------------------------------------------
import sys
import pandas as pd
#
# ------------------------------------------------------------------
sys.stderr.write("*** 開始 ***\n")
#
df = pd.DataFrame([
        ["t1271","千葉",93416,"2003-11-5"],
        ["t1272","勝浦",47573,"2003-6-14"],
        ["t1273","市原",28451,"2003-9-25"],
        ["t1274","流山",39842,"2003-8-28"],
        ["t1275","八千代",27896,"2003-8-8"],
        ["t1276","我孫子",13175,"2003-1-15"],
        ["t1277","鴨川",85234,"2003-10-21"]])

print(df)
#
path="./cities.html"
#
df.to_html(path,header=None,index=None)
#
sys.stderr.write("*** 終了 ***\n")
# ------------------------------------------------------------------

html ファイルの読み込み

html_read.py

#! /usr/bin/python
# -*- coding: utf-8 -*-
#
#   html_read.py
#
#                   Oct/01/2018
# ------------------------------------------------------------------
import sys
import pandas as pd
#
# ------------------------------------------------------------------
sys.stderr.write("*** 開始 ***\n")
#
file_html = "./cities.html"
#
df=pd.read_html(file_html,header=None,encoding='utf8')
print(df[0])
#
sys.stderr.write("*** 終了 ***\n")
# ------------------------------------------------------------------

html ファイル

cities.html

<table border="1" class="dataframe">
  <tbody>
    <tr>
      <td>t1271</td>
      <td>千葉</td>
      <td>93416</td>
      <td>2003-11-5</td>
    </tr>
    <tr>
      <td>t1272</td>
      <td>勝浦</td>
      <td>47573</td>
      <td>2003-6-14</td>
    </tr>
    <tr>
      <td>t1273</td>
      <td>市原</td>
      <td>28451</td>
      <td>2003-9-25</td>
    </tr>
    <tr>
      <td>t1274</td>
      <td>流山</td>
      <td>39842</td>
      <td>2003-8-28</td>
    </tr>
    <tr>
      <td>t1275</td>
      <td>八千代</td>
      <td>27896</td>
      <td>2003-8-8</td>
    </tr>
    <tr>
      <td>t1276</td>
      <td>我孫子</td>
      <td>13175</td>
      <td>2003-1-15</td>
    </tr>
    <tr>
      <td>t1277</td>
      <td>鴨川</td>
      <td>85234</td>
      <td>2003-10-21</td>
    </tr>
  </tbody>
</table>