Skip to content

Commit

Permalink
Update
Browse files Browse the repository at this point in the history
  • Loading branch information
@kelu124
kelu124 committed Jan 11, 2024
1 parent 2c020f5 commit f81838c
Show file tree
Hide file tree
Showing 555 changed files with 15,475 additions and 6,590 deletions.
126 changes: 63 additions & 63 deletions 00.getURLs.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -40,18 +40,18 @@
"data": {
"text/plain": [
"(12,\n",
" ['https://kghosh.substack.com/p/20231111',\n",
" 'https://kghosh.substack.com/p/20231022',\n",
" 'https://kghosh.substack.com/p/20231230',\n",
" 'https://kghosh.substack.com/p/20231029',\n",
" 'https://kghosh.substack.com/p/20231017',\n",
" ['https://kghosh.substack.com/p/some-guesses-about-2024',\n",
" 'https://kghosh.substack.com/p/20231105',\n",
" 'https://kghosh.substack.com/p/20231119',\n",
" 'https://kghosh.substack.com/p/20231029',\n",
" 'https://kghosh.substack.com/p/20231111',\n",
" 'https://kghosh.substack.com/p/20231203',\n",
" 'https://kghosh.substack.com/p/20231209',\n",
" 'https://kghosh.substack.com/p/20231126',\n",
" 'https://kghosh.substack.com/p/20230109',\n",
" 'https://kghosh.substack.com/p/20231230',\n",
" 'https://kghosh.substack.com/p/20231119',\n",
" 'https://kghosh.substack.com/p/20221217',\n",
" 'https://kghosh.substack.com/p/some-guesses-about-2024',\n",
" 'https://kghosh.substack.com/p/20231209'])"
" 'https://kghosh.substack.com/p/20231022'])"
]
},
"execution_count": 2,
Expand Down Expand Up @@ -85,18 +85,18 @@
"name": "stdout",
"output_type": "stream",
"text": [
"20231111 exists.\n",
"20231022 exists.\n",
"20231230 saved\n",
"20231029 exists.\n",
"20231017 exists.\n",
"some-guesses-about-2024 exists.\n",
"20231105 exists.\n",
"20231119 exists.\n",
"20231029 exists.\n",
"20231111 exists.\n",
"20231203 exists.\n",
"20231209 exists.\n",
"20231126 exists.\n",
"20221217 saved\n",
"some-guesses-about-2024 saved\n",
"20231209 exists.\n"
"20230109 saved\n",
"20231230 exists.\n",
"20231119 exists.\n",
"20221217 exists.\n",
"20231022 exists.\n"
]
}
],
Expand Down Expand Up @@ -140,7 +140,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"There are 1272 pages saved.\n"
"There are 1317 pages saved.\n"
]
},
{
Expand Down Expand Up @@ -189,7 +189,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"1875\n"
"1901\n"
]
},
{
Expand Down Expand Up @@ -256,38 +256,38 @@
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1870</th>\n",
" <th>1896</th>\n",
" <td>.cache/fully-homomorphic-encryption</td>\n",
" <td>b'https://substackcdn.com/image/fetch/f_auto,q...</td>\n",
" <td>f0a23dcd98c2fdf0a3fd523a04e7c255</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1871</th>\n",
" <th>1897</th>\n",
" <td>.cache/some-guesses-about-2024</td>\n",
" <td>b'https://substackcdn.com/image/fetch/f_auto,q...</td>\n",
" <td>b82a7509d34dc6974ca9036c0d80ba7d</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1872</th>\n",
" <th>1898</th>\n",
" <td>.cache/some-guesses-about-2024</td>\n",
" <td>b'https://www2.deloitte.com/us/en/insights/ind...</td>\n",
" <td>c1f03407e92d82ff6f8e3bc04f8996c2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1873</th>\n",
" <th>1899</th>\n",
" <td>.cache/when-the-tide-of-ai-generated-texts</td>\n",
" <td>b'https://substackcdn.com/image/fetch/f_auto,q...</td>\n",
" <td>d256bfc733bfe7fe3f55726967800605</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1874</th>\n",
" <th>1900</th>\n",
" <td>.cache/when-the-tide-of-ai-generated-texts</td>\n",
" <td>b'https://bronasbooks.com/2022/01/17/the-libra...</td>\n",
" <td>228ce5d138c39687cacf2eae975950d7</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1844 rows × 3 columns</p>\n",
"<p>1868 rows × 3 columns</p>\n",
"</div>"
],
"text/plain": [
Expand All @@ -298,11 +298,11 @@
"3 .cache/20220118 \n",
"4 .cache/20220118 \n",
"... ... \n",
"1870 .cache/fully-homomorphic-encryption \n",
"1871 .cache/some-guesses-about-2024 \n",
"1872 .cache/some-guesses-about-2024 \n",
"1873 .cache/when-the-tide-of-ai-generated-texts \n",
"1874 .cache/when-the-tide-of-ai-generated-texts \n",
"1896 .cache/fully-homomorphic-encryption \n",
"1897 .cache/some-guesses-about-2024 \n",
"1898 .cache/some-guesses-about-2024 \n",
"1899 .cache/when-the-tide-of-ai-generated-texts \n",
"1900 .cache/when-the-tide-of-ai-generated-texts \n",
"\n",
" url \\\n",
"0 b'https://www.gov.wales/sites/default/files/pu... \n",
Expand All @@ -311,11 +311,11 @@
"3 b'https://www.futuregenerations.wales/about-us... \n",
"4 b'https://www.bbc.com/future/article/20230215-... \n",
"... ... \n",
"1870 b'https://substackcdn.com/image/fetch/f_auto,q... \n",
"1871 b'https://substackcdn.com/image/fetch/f_auto,q... \n",
"1872 b'https://www2.deloitte.com/us/en/insights/ind... \n",
"1873 b'https://substackcdn.com/image/fetch/f_auto,q... \n",
"1874 b'https://bronasbooks.com/2022/01/17/the-libra... \n",
"1896 b'https://substackcdn.com/image/fetch/f_auto,q... \n",
"1897 b'https://substackcdn.com/image/fetch/f_auto,q... \n",
"1898 b'https://www2.deloitte.com/us/en/insights/ind... \n",
"1899 b'https://substackcdn.com/image/fetch/f_auto,q... \n",
"1900 b'https://bronasbooks.com/2022/01/17/the-libra... \n",
"\n",
" hash \n",
"0 3b92dc627d73b0d586fcff194b697c89 \n",
Expand All @@ -324,13 +324,13 @@
"3 3938700a79bbde32972657f9eb7b1b69 \n",
"4 32228bbf929d81d39a1808dd9b7c4493 \n",
"... ... \n",
"1870 f0a23dcd98c2fdf0a3fd523a04e7c255 \n",
"1871 b82a7509d34dc6974ca9036c0d80ba7d \n",
"1872 c1f03407e92d82ff6f8e3bc04f8996c2 \n",
"1873 d256bfc733bfe7fe3f55726967800605 \n",
"1874 228ce5d138c39687cacf2eae975950d7 \n",
"1896 f0a23dcd98c2fdf0a3fd523a04e7c255 \n",
"1897 b82a7509d34dc6974ca9036c0d80ba7d \n",
"1898 c1f03407e92d82ff6f8e3bc04f8996c2 \n",
"1899 d256bfc733bfe7fe3f55726967800605 \n",
"1900 228ce5d138c39687cacf2eae975950d7 \n",
"\n",
"[1844 rows x 3 columns]"
"[1868 rows x 3 columns]"
]
},
"execution_count": 7,
Expand Down Expand Up @@ -421,38 +421,38 @@
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1870</th>\n",
" <th>1896</th>\n",
" <td>.cache/fully-homomorphic-encryption</td>\n",
" <td>b'https://substackcdn.com/image/fetch/f_auto,q...</td>\n",
" <td>f0a23dcd98c2fdf0a3fd523a04e7c255</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1871</th>\n",
" <th>1897</th>\n",
" <td>.cache/some-guesses-about-2024</td>\n",
" <td>b'https://substackcdn.com/image/fetch/f_auto,q...</td>\n",
" <td>b82a7509d34dc6974ca9036c0d80ba7d</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1872</th>\n",
" <th>1898</th>\n",
" <td>.cache/some-guesses-about-2024</td>\n",
" <td>b'https://www2.deloitte.com/us/en/insights/ind...</td>\n",
" <td>c1f03407e92d82ff6f8e3bc04f8996c2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1873</th>\n",
" <th>1899</th>\n",
" <td>.cache/when-the-tide-of-ai-generated-texts</td>\n",
" <td>b'https://substackcdn.com/image/fetch/f_auto,q...</td>\n",
" <td>d256bfc733bfe7fe3f55726967800605</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1874</th>\n",
" <th>1900</th>\n",
" <td>.cache/when-the-tide-of-ai-generated-texts</td>\n",
" <td>b'https://bronasbooks.com/2022/01/17/the-libra...</td>\n",
" <td>228ce5d138c39687cacf2eae975950d7</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1844 rows × 3 columns</p>\n",
"<p>1868 rows × 3 columns</p>\n",
"</div>"
],
"text/plain": [
Expand All @@ -463,11 +463,11 @@
"3 .cache/20220118 \n",
"4 .cache/20220118 \n",
"... ... \n",
"1870 .cache/fully-homomorphic-encryption \n",
"1871 .cache/some-guesses-about-2024 \n",
"1872 .cache/some-guesses-about-2024 \n",
"1873 .cache/when-the-tide-of-ai-generated-texts \n",
"1874 .cache/when-the-tide-of-ai-generated-texts \n",
"1896 .cache/fully-homomorphic-encryption \n",
"1897 .cache/some-guesses-about-2024 \n",
"1898 .cache/some-guesses-about-2024 \n",
"1899 .cache/when-the-tide-of-ai-generated-texts \n",
"1900 .cache/when-the-tide-of-ai-generated-texts \n",
"\n",
" url \\\n",
"0 b'https://www.gov.wales/sites/default/files/pu... \n",
Expand All @@ -476,11 +476,11 @@
"3 b'https://www.futuregenerations.wales/about-us... \n",
"4 b'https://www.bbc.com/future/article/20230215-... \n",
"... ... \n",
"1870 b'https://substackcdn.com/image/fetch/f_auto,q... \n",
"1871 b'https://substackcdn.com/image/fetch/f_auto,q... \n",
"1872 b'https://www2.deloitte.com/us/en/insights/ind... \n",
"1873 b'https://substackcdn.com/image/fetch/f_auto,q... \n",
"1874 b'https://bronasbooks.com/2022/01/17/the-libra... \n",
"1896 b'https://substackcdn.com/image/fetch/f_auto,q... \n",
"1897 b'https://substackcdn.com/image/fetch/f_auto,q... \n",
"1898 b'https://www2.deloitte.com/us/en/insights/ind... \n",
"1899 b'https://substackcdn.com/image/fetch/f_auto,q... \n",
"1900 b'https://bronasbooks.com/2022/01/17/the-libra... \n",
"\n",
" hash \n",
"0 3b92dc627d73b0d586fcff194b697c89 \n",
Expand All @@ -489,13 +489,13 @@
"3 3938700a79bbde32972657f9eb7b1b69 \n",
"4 32228bbf929d81d39a1808dd9b7c4493 \n",
"... ... \n",
"1870 f0a23dcd98c2fdf0a3fd523a04e7c255 \n",
"1871 b82a7509d34dc6974ca9036c0d80ba7d \n",
"1872 c1f03407e92d82ff6f8e3bc04f8996c2 \n",
"1873 d256bfc733bfe7fe3f55726967800605 \n",
"1874 228ce5d138c39687cacf2eae975950d7 \n",
"1896 f0a23dcd98c2fdf0a3fd523a04e7c255 \n",
"1897 b82a7509d34dc6974ca9036c0d80ba7d \n",
"1898 c1f03407e92d82ff6f8e3bc04f8996c2 \n",
"1899 d256bfc733bfe7fe3f55726967800605 \n",
"1900 228ce5d138c39687cacf2eae975950d7 \n",
"\n",
"[1844 rows x 3 columns]"
"[1868 rows x 3 columns]"
]
},
"execution_count": 8,
Expand Down
Loading

0 comments on commit f81838c

Please sign in to comment.