Spaces:
Running
Running
File size: 4,884 Bytes
91eaff6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 |
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Convert the markdown generated from Jupyter notebooks to preserve
rendered images, etc.
"""
import os
import pathlib
import re
import sys
import time
import traceback
import typing
from icecream import ic # pylint: disable=E0401
from selenium import webdriver # pylint: disable=E0401
class Converter:
"""
HTML/Markdown conversion
"""
PAT_HEADER = re.compile(r"^(```python\n\# for use.*production:\n.*\n```\n)", re.MULTILINE)
PAT_SOURCE = re.compile(r"\s+src\=\"(\S+)\"")
REPLACEMENT_HEADER: str = """
!!! note
To run this notebook in JupyterLab, load [`examples/{}.ipynb`]({}/examples/{}.ipynb)
"""
def __init__ (
self,
src_url: str,
) -> None:
"""
Constructor.
"""
self.src_url: str = src_url
def replace_sys_header (
self,
text: str,
stem: str,
*,
debug: bool = False,
) -> str:
"""
Replace the initial cell in a tutorial notebook.
"""
output: typing.List[ str ] = []
for chunk in self.PAT_HEADER.split(text):
m_header: typing.Optional[ re.Match ] = self.PAT_HEADER.match(chunk)
if debug:
ic(m_header)
if m_header:
header: str = self.REPLACEMENT_HEADER.format(stem, self.src_url, stem)
output.append(header)
else:
output.append(chunk)
return "\n".join(output)
def get_pyvis_html (
self,
iframe: str,
*,
debug: bool = False,
) -> str:
"""
Locate the HTML files generated by `PyVis` if any.
This assumes the HTML files are named `tmp.fig*.*`
"""
source_html: typing.Optional[ str ] = None
m_source: typing.Optional[ re.Match ] = self.PAT_SOURCE.search(iframe)
if m_source:
source_html = m_source.group(1)
if debug:
ic(source_html)
if "tmp.fig" not in source_html: # type: ignore
# <iframe/> wasn't generated by PyVis
source_html = None
return source_html # type: ignore
def render_screenshot (
self,
source_html: str,
source_png,
) -> None:
"""
use Selenium to render `source_png` from `source_html`
"""
#chrome_path = os.getcwd() + "/chromedriver"
#chrome_options = Options()
browser: webdriver.Chrome = webdriver.Chrome()
browser.get(source_html)
time.sleep(10)
browser.get_screenshot_as_file(source_png)
browser.quit()
def replace_pyvis_iframe (
self,
text: str,
parent: pathlib.Path,
stem: str,
*,
debug: bool = False,
) -> str:
"""
Substitute static images for the rendered graphs.
"""
output: typing.List[ str ] = []
in_iframe: bool = False
for line in text.split("\n"):
if line.startswith("<iframe"):
in_iframe = True
if not in_iframe:
output.append(line)
elif line.strip().startswith("src="):
src_html: str = self.get_pyvis_html(line)
src_png: str = src_html.replace(".html", ".png")
if debug:
ic(src_png)
try:
os.mkdir(f"{parent}/{stem}_files")
except: # pylint: disable=W0702
pass
self.render_screenshot(
f"file://{os.getcwd()}/examples/{src_html}",
f"{parent}/{stem}_files/{src_png}",
)
output.append(f"")
if line.startswith("></iframe>"):
in_iframe = False
return "\n".join(output)
if __name__ == "__main__":
try:
conv: Converter = Converter(
"https://github.com/DerwenAI/textgraphs/blob/main",
)
filename: pathlib.Path = pathlib.Path(sys.argv[1])
_parent: pathlib.Path = filename.parent
_stem: str = filename.stem
ic(filename, _parent, _stem)
with open(filename, "r", encoding = "utf-8") as fp:
html: str = fp.read()
html = conv.replace_sys_header( # pylint: disable=C0103
html,
_stem,
debug = False, # True
)
#print(text)
#sys.exit(0)
html = conv.replace_pyvis_iframe( # pylint: disable=C0103
html,
_parent,
_stem,
debug = True, # False
)
with open(filename, "w", encoding = "utf-8") as fp:
fp.write(html)
except Exception as ex: # pylint: disable=W0718
ic(ex)
traceback.print_exc()
|