Switch eBook PDF generation from WeasyPrint to Prince

src/README.md

@@ -58,13 +58,7 @@ npm install
 npm run generate
 ```
 
-3. For generating PDFs of the ebook, WeasyPrint will need some additional libraries:
-
-```
-brew install cairo
-brew install pango
-brew install gdk-pixbuf
-```
+3. For generating PDFs of the ebook, you need to install Prince. Follow the instructions on [the Prince Website](https://www.princexml.com/).
 
 4. To actually generate the ebooks, start your local server, then run the following:
 
@@ -75,6 +69,22 @@ npm run ebook_2019_ja
 
 (TODO: make this a script to handle all languages and years at some point)
 
+It is also possible to generate the ebook from the website, with some optional params (e.g. to print it!)
+
+```
+prince "https://almanac.httparchive.org/en/2019/ebook?print&inside-margin=4cm" -o web_almanac_2019_en.pdf --pdf-profile='PDF/UA-1'
+```
+
+Note `--pdf-profile='PDF/UA-1'` may not be needed if just intend to print.
+
+Params accepted are:
+
+- print - this ads left, right pages, footnotes, and sets roman numerals for front matter page numbers and adds footnotes. It is used by default when running `npm run ebook_2019_en` but we could change that if prefer a less print-like ebook.
+- page-size - this allows you to override the default page size of A4
+- inside-margin - this allows you to set an inside margin for binding (e.g. on right for left hand pages and vice versa)
+
+You can also download the HTML and override the inline styles there if you want to customise this for something we haven;t exposed as a param.
+
 ## Deploying changes
 
 If you've been added to the "App Engine Deployers" role in the GCP project, you're able to push code changes to the production website.

src/main.py

@@ -130,21 +130,39 @@ def get_ebook_methodology(lang, year):
         return False
 
     methodology_maincontent = methodology_maincontent.group(1)
+    # Replace methodology links to full anchor link (e.g. #introduction -> #methodology-introduction)
     methodology_maincontent = re.sub('href="#', 'href="#methodology-', methodology_maincontent)
+    # Replace header ids to full id (e.g. <h2 id="introduction"> -> <h2 id="methodology-introduction">)
     methodology_maincontent = re.sub('<h([0-6]) id="', '<h\\1 id="methodology-', methodology_maincontent)
+    # Replace home-relative URLS generated by url_for (e.g. /en/2019/ -> #)
     methodology_maincontent = re.sub('href="\/%s\/%s\/' % (lang, year), 'href="#', methodology_maincontent)
+    # For external links add footnote span
+    methodology_maincontent = re.sub('href="http(.*?)"(.*?)>(.*?)<\/a>', 'href="http\\1"\\2>\\3<span class="fn">http\\1</span></a>', methodology_maincontent)
+    # Replace figure image links to full site, to avoid 127.0.0.1:8080 links
     methodology_maincontent = re.sub('href="\/', 'href="https://almanac.httparchive.org/', methodology_maincontent)
+    # Replace other chapter references with hash to anchor link (e.g. ./javascript#fig-1 -> #javascript-fig-1)
+    methodology_maincontent = re.sub('href="./([a-z0-9-]*)#', 'href="#\\1-', methodology_maincontent)
+    # Replace other chapter references to anchor link (e.g. ./javascript -> #javascript)
     methodology_maincontent = re.sub('href="\.\/', 'href="#', methodology_maincontent)
+    # Replace double-hashed URLs (e.g. #contributors#patrickhulce -> #contributors-patrickhulce)
     methodology_maincontent = re.sub('href="#([a-z0-9-]*)#', 'href="#\\1-', methodology_maincontent)
+    # Remove lazy-loading attributes
+    methodology_maincontent = re.sub(' loading="lazy"', '', methodology_maincontent)
     return methodology_maincontent
 
 
+# This function takes a string and adds the footnote links for printing
+def add_footnote_links(html):
+    return re.sub('href="http(.*?)"(.*?)>(.*?)<\/a>', 'href="http\\1"\\2>\\3<span class="fn">http\\1</span></a>', html)
+
+
 # Make these functions available in templates.
 app.jinja_env.globals['get_view_args'] = get_view_args
 app.jinja_env.globals['chapter_lang_exists'] = chapter_lang_exists
 app.jinja_env.globals['ebook_exists'] = ebook_exists
 app.jinja_env.globals['HTTP_STATUS_CODES'] = HTTP_STATUS_CODES
 app.jinja_env.globals['get_ebook_methodology'] = get_ebook_methodology
+app.jinja_env.globals['add_footnote_links'] = add_footnote_links
 
 
 @app.route('/<lang>/<year>/')

src/package.json

@@ -15,8 +15,8 @@
   "homepage": "https://github.com/HTTPArchive/almanac.httparchive.org#readme",
   "scripts": {
     "generate": "node ./tools/generate",
-    "ebook_2019_en": "weasyprint http://127.0.0.1:8080/en/2019/ebook static/pdfs/web_almanac_2019_en.pdf",
-    "ebook_2019_ja": "weasyprint http://127.0.0.1:8080/ja/2019/ebook static/pdfs/web_almanac_2019_ja.pdf",
+    "ebook_2019_en": "prince http://127.0.0.1:8080/en/2019/ebook?print -o static/pdfs/web_almanac_2019_en.pdf --pdf-profile='PDF/UA-1'",
+    "ebook_2019_ja": "prince http://127.0.0.1:8080/ja/2019/ebook?print -o static/pdfs/web_almanac_2019_ja.pdf --pdf-profile='PDF/UA-1'",
     "deploy": "echo \"Y\" | gcloud app deploy --project webalmanac --stop-previous-version"
   },
   "devDependencies": {