pypdf2 has moved to pypdf

CHANGELOG.bak

@@ -2,6 +2,10 @@
 
 <!-- do not remove -->
 
+## 0.0.6
+
+- Make read_gh_repo default to returning dict
+
 ## 0.0.5
 
 - Bug fix in __init__ for read_gh_repo

CHANGELOG.md

@@ -2,6 +2,11 @@
 
 <!-- do not remove -->
 
+## 0.0.7
+
+- Update to dependencies
+
+
 ## 0.0.6
 
 - Make read_gh_repo default to returning dict

README.md

@@ -33,8 +33,10 @@ rd.read_url('https://www.answer.ai/')[:200]
     'Answer.AI\n\n  * __\n  * __\n\n# Answer.AI - Practical AI R&D\n\n##### Categories\n\nAll (33)\n\nai (20)\n\ncoding (5)\n\ncompany (2)\n\ncourses (1)\n\neducation (1)\n\ninterview (1)\n\nopen-source (14)\n\npolicy (4)\n\nproduct'
 
 Other arguments are always optional, but can be useful at times. For
-example, the `heavy` argument in `read_url` allows you to do a heavy
-scrape with a contactless browser using `playwrightnb`.
+example, the `heavy` argument in
+[`read_url`](https://AnswerDotAI.github.io/contextkit/read.html#read_url)
+allows you to do a heavy scrape with a contactless browser using
+`playwrightnb`.
 
 ``` python
 rd.read_url('https://www.answer.ai/',heavy=True)[:200]

contextkit/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.0.6"
+__version__ = "0.0.7"
 
 from . import read
 from .read import read_url, read_gist, read_gh_file, read_file, read_dir, read_pdf, read_yt_transcript, read_google_sheet, read_gdoc, read_arxiv, read_gh_repo

contextkit/read.py

@@ -15,7 +15,7 @@
 import requests
 import fnmatch, mimetypes
 
-from PyPDF2 import PdfReader
+from pypdf import PdfReader
 from toolslm.download import html2md, read_html
 
 import tempfile, subprocess, os, re, shutil

nbs/00_read.ipynb

@@ -63,7 +63,7 @@
     "import requests\n",
     "import fnmatch, mimetypes\n",
     "\n",
-    "from PyPDF2 import PdfReader\n",
+    "from pypdf import PdfReader\n",
     "from toolslm.download import html2md, read_html\n",
     "\n",
     "import tempfile, subprocess, os, re, shutil\n",
@@ -432,7 +432,7 @@
     {
      "data": {
       "text/plain": [
-       "' \\n  \\n   \\nThis is a test PDF document. \\nIf you can read this, you have Adobe Acrobat Reader installed on your computer. '"
+       "' \\n \\n \\n \\n \\n \\nThis is a test PDF document. \\nIf you can read this, you have Adobe Acrobat Reader installed on your computer. '"
       ]
      },
      "execution_count": null,

settings.ini

@@ -1,7 +1,7 @@
 [DEFAULT]
 repo = contextkit
 lib_name = contextkit
-version = 0.0.6
+version = 0.0.7
 min_python = 3.11
 license = apache2
 black_formatting = False
@@ -26,7 +26,7 @@ keywords = nbdev jupyter notebook python
 language = English
 status = 3
 user = AnswerDotAI
-requirements = python-fasthtml httpx toolslm fastcore llms-txt PyPDF2 youtube_transcript_api pytube playwrightnb
+requirements = python-fasthtml httpx toolslm fastcore llms-txt pypdf youtube_transcript_api pytube playwrightnb
 readme_nb = index.ipynb
 allowed_metadata_keys = 
 allowed_cell_metadata_keys =