Contact
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutSign UpSign In
| Download

Python Data Science Handbook

Views: 90273
1
"""

2
This script copies all notebooks from the book into the website directory, and

3
creates pages which wrap them and link together.

4
"""

5
import os

6
import nbformat

7
import shutil

8


9
PAGEFILE = """title: {title}

10
url:

11
save_as: {htmlfile}

12
Template: {template}

13


14
{{% notebook notebooks/{notebook_file} cells[{cells}] %}}

15
"""

16


17
INTRO_TEXT = """This website contains the full text of the [Python Data Science Handbook](http://shop.oreilly.com/product/0636920034919.do) by Jake VanderPlas; the content is available [on GitHub](https://github.com/jakevdp/PythonDataScienceHandbook) in the form of Jupyter notebooks.

18


19
The text is released under the [CC-BY-NC-ND license](https://creativecommons.org/licenses/by-nc-nd/3.0/us/legalcode), and code is released under the [MIT license](https://opensource.org/licenses/MIT).

20


21
If you find this content useful, please consider supporting the work by [buying the book](http://shop.oreilly.com/product/0636920034919.do)!

22
"""

23


24


25
def abspath_from_here(*args):

26
    here = os.path.dirname(__file__)

27
    path = os.path.join(here, *args)

28
    return os.path.abspath(path)

29


30
NB_SOURCE_DIR = abspath_from_here('..', 'notebooks')

31
NB_DEST_DIR = abspath_from_here('content', 'notebooks')

32
PAGE_DEST_DIR = abspath_from_here('content', 'pages')

33


34


35
def copy_notebooks():

36
    nblist = sorted(nb for nb in os.listdir(NB_SOURCE_DIR)

37
                    if nb.endswith('.ipynb'))

38
    name_map = {nb: nb.rsplit('.', 1)[0].lower() + '.html'

39
                for nb in nblist}

40


41
    figsource = abspath_from_here('..', 'notebooks', 'figures')

42
    figdest = abspath_from_here('content', 'figures')

43


44
    if os.path.exists(figdest):

45
        shutil.rmtree(figdest)

46
    shutil.copytree(figsource, figdest)

47


48
    figurelist = os.listdir(abspath_from_here('content', 'figures'))

49
    figure_map = {os.path.join('figures', fig) : os.path.join('/PythonDataScienceHandbook/figures', fig)

50
                  for fig in figurelist}

51


52
    for nb in nblist:

53
        base, ext = os.path.splitext(nb)

54
        print('-', nb)

55


56
        content = nbformat.read(os.path.join(NB_SOURCE_DIR, nb),

57
                                as_version=4)

58


59
        if nb == 'Index.ipynb':

60
            cells = '1:'

61
            template = 'page'

62
            title = 'Python Data Science Handbook'

63
            content.cells[2].source = INTRO_TEXT

64
        else:

65
            cells = '2:'

66
            template = 'booksection'

67
            title = content.cells[2].source

68
            if not title.startswith('#') or len(title.splitlines()) > 1:

69
                raise ValueError('title not found in third cell')

70
            title = title.lstrip('#').strip()

71


72
            # put nav below title

73
            content.cells[0], content.cells[1], content.cells[2] = content.cells[2], content.cells[0], content.cells[1]

74


75
        # Replace internal URLs and figure links in notebook

76
        for cell in content.cells:

77
            if cell.cell_type == 'markdown':

78
                for nbname, htmlname in name_map.items():

79
                    if nbname in cell.source:

80
                        cell.source = cell.source.replace(nbname, htmlname)

81
                for figname, newfigname in figure_map.items():

82
                    if figname in cell.source:

83
                        cell.source = cell.source.replace(figname, newfigname)

84
                        

85
        nbformat.write(content, os.path.join(NB_DEST_DIR, nb))

86


87
        pagefile = os.path.join(PAGE_DEST_DIR, base + '.md')

88
        htmlfile = base.lower() + '.html'

89
        with open(pagefile, 'w') as f:

90
            f.write(PAGEFILE.format(title=title,

91
                                    htmlfile=htmlfile,

92
                                    notebook_file=nb,

93
                                    template=template,

94
                                    cells=cells))

95


96
if __name__ == '__main__':

97
    copy_notebooks()

98


99
    

100


101