Download stories and build epubs with FanFicFare
FanFicFare adapters fetch metadata and chapters, and its epub writer builds each book from the store. Environment variables configure the app, and a default personal.ini is copied to the config folder on first start.
This commit is contained in:
@@ -0,0 +1,155 @@
|
||||
"""Build an epub from stored data without network access, then read it back."""
|
||||
|
||||
import base64
|
||||
import datetime
|
||||
import re
|
||||
import zipfile
|
||||
|
||||
import pytest
|
||||
from defusedxml import ElementTree
|
||||
|
||||
from bindery import config, fff
|
||||
from bindery.rules import compile_rules, normalize_rules
|
||||
|
||||
URL = "https://www.royalroad.com/fiction/1234/test-story"
|
||||
PNG = base64.b64decode(
|
||||
"iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg=="
|
||||
)
|
||||
IMG_URL = "https://www.royalroadcdn.com/public/img.png"
|
||||
COVER = {"url": "https://www.royalroadcdn.com/public/covers/1234.png", "ext": "png", "mime": "image/png", "data": PNG}
|
||||
|
||||
|
||||
def metahtml(url=URL):
|
||||
adapter = fff.get_adapter(url)
|
||||
story = adapter.story
|
||||
story.setMetadata("title", "Test Story")
|
||||
story.addToList("author", "Writer")
|
||||
story.addToList("authorId", "42")
|
||||
story.setMetadata("description", "<p>About the story</p>")
|
||||
story.setMetadata("datePublished", datetime.datetime(2024, 1, 2))
|
||||
story.setMetadata("dateUpdated", datetime.datetime(2024, 3, 4))
|
||||
story.addToList("genre", "Fantasy")
|
||||
return story.dump_html_metadata()
|
||||
|
||||
|
||||
def chapters():
|
||||
base = "https://www.royalroad.com/fiction/1234/test-story/chapter/{0}/c{0}"
|
||||
return [
|
||||
{"url": base.format(10), "title": "One", "html": '<div><p class="rnd1">Zorian wakes.</p></div>'},
|
||||
{"url": base.format(11), "title": "Two", "html": f'<div><p>Picture</p><img src="{IMG_URL}"/></div>'},
|
||||
{"url": base.format(15), "title": "Three", "html": "<div><p>Zorian again.</p></div>"},
|
||||
]
|
||||
|
||||
|
||||
def test_build_and_read_back(tmp_path):
|
||||
rules = compile_rules(normalize_rules([{"pattern": "Zorian", "replacement": "Z"}]))
|
||||
out = tmp_path / "book.epub"
|
||||
images = [{"url": IMG_URL, "ext": "png", "mime": "image/png", "data": PNG}]
|
||||
meta = fff.build_epub(URL, metahtml(), chapters(), images, None, rules, {"title": "Kept Title"}, out)
|
||||
assert meta["title"] == "Kept Title"
|
||||
assert meta["authors"] == ["Writer"]
|
||||
assert meta["pubdate"].startswith("2024-01-02")
|
||||
|
||||
with zipfile.ZipFile(out) as z:
|
||||
names = z.namelist()
|
||||
text = "".join(z.read(n).decode("utf-8", "ignore") for n in names if n.endswith(".xhtml"))
|
||||
opf = z.read("content.opf").decode()
|
||||
assert "Z wakes." in text and "Zorian" not in text
|
||||
assert any(n.startswith("OEBPS/images/ffdl-") and n.endswith(".png") for n in names)
|
||||
assert re.search(r"<dc:title[^>]*>Kept Title</dc:title>", opf)
|
||||
|
||||
contents = fff.read_epub(out)
|
||||
assert [c["title"] for c in contents.chapters] == ["One", "Two", "Three"]
|
||||
assert [c["url"] for c in contents.chapters] == [c["url"] for c in chapters()]
|
||||
assert IMG_URL in contents.chapters[1]["html"]
|
||||
assert contents.images and contents.images[0]["url"] == IMG_URL
|
||||
|
||||
|
||||
def test_a_title_with_entities_builds_and_imports_in_fanficfare_form(tmp_path):
|
||||
# FanFicFare's form, as the site titles in the store have it.
|
||||
title = "Folly & Magic <1>"
|
||||
out = tmp_path / "book.epub"
|
||||
fff.build_epub(URL, metahtml(), [dict(chapters()[0], title=title)], [], None, [], {}, out)
|
||||
with zipfile.ZipFile(out) as z:
|
||||
for name in z.namelist():
|
||||
if name.endswith((".xhtml", ".ncx", ".opf")):
|
||||
ElementTree.fromstring(z.read(name))
|
||||
# An import stores the same title as a download, so the next update finds no rename.
|
||||
assert fff.read_epub(out).chapters[0]["title"] == title
|
||||
assert fff.plain_title(title) == "Folly & Magic <1>"
|
||||
assert fff.escape_title("Folly & Magic <1>") == title
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
("personal_ini", "expected"),
|
||||
[
|
||||
("", "coveronly"),
|
||||
("[www.royalroad.com]\ninclude_images:false\n", "coveronly"),
|
||||
("[defaults]\ninclude_images:true\n", "true"),
|
||||
("[defaults]\ninclude_images:coveronly\n", "coveronly"),
|
||||
],
|
||||
)
|
||||
def test_include_images_is_never_off(personal_ini, expected, tmp_path, monkeypatch):
|
||||
path = tmp_path / "personal.ini"
|
||||
path.write_text(personal_ini)
|
||||
monkeypatch.setattr(config, "PERSONAL_INI", path)
|
||||
assert fff.get_configuration(URL).getConfig("include_images") == expected
|
||||
|
||||
|
||||
@pytest.mark.parametrize("personal_ini", ["", "[defaults]\ninclude_images:false\n"])
|
||||
def test_the_cover_goes_in_the_epub_without_include_images(personal_ini, tmp_path, monkeypatch):
|
||||
path = tmp_path / "personal.ini"
|
||||
path.write_text(personal_ini)
|
||||
monkeypatch.setattr(config, "PERSONAL_INI", path)
|
||||
out = tmp_path / "book.epub"
|
||||
fff.build_epub(URL, metahtml(), chapters(), [], COVER, [], {}, out)
|
||||
with zipfile.ZipFile(out) as z:
|
||||
names = z.namelist()
|
||||
opf = z.read("content.opf").decode()
|
||||
assert "OEBPS/cover.xhtml" in names
|
||||
assert any(n.startswith("OEBPS/images/cover.") for n in names)
|
||||
assert re.search(r'<meta name="cover" content="[^"]+"', opf)
|
||||
|
||||
|
||||
def test_locked_fields_replace_site_metadata(tmp_path):
|
||||
out = tmp_path / "book.epub"
|
||||
overrides = {
|
||||
"title": "Kept Title",
|
||||
"authors": ["Pen Name", "Co Writer"],
|
||||
"comments": "<p>Kept blurb</p>",
|
||||
"series": ["Kept Saga", 3.0],
|
||||
"pubdate": "2019-05-06T00:00:00+00:00",
|
||||
"languages": "de",
|
||||
"tags": ["mine", "reread"],
|
||||
}
|
||||
meta = fff.build_epub(URL, metahtml(), chapters(), [], None, [], overrides, out)
|
||||
assert meta["authors"] == ["Pen Name", "Co Writer"]
|
||||
assert meta["tags"] == ["mine", "reread"]
|
||||
with zipfile.ZipFile(out) as z:
|
||||
opf = z.read("content.opf").decode()
|
||||
assert re.findall(r"<dc:creator[^>]*>([^<]*)</dc:creator>", opf) == ["Pen Name", "Co Writer"]
|
||||
assert re.findall(r"<dc:subject>([^<]*)</dc:subject>", opf) == ["mine", "reread"]
|
||||
assert 'name="calibre:series" content="Kept Saga"' in opf
|
||||
assert 'name="calibre:series_index" content="3.00"' in opf
|
||||
assert "<dc:language>de</dc:language>" in opf
|
||||
assert "2019-05-06" in opf
|
||||
assert "Kept blurb" in opf
|
||||
|
||||
|
||||
def test_unlocked_fields_keep_site_metadata(tmp_path):
|
||||
out = tmp_path / "book.epub"
|
||||
meta = fff.build_epub(URL, metahtml(), chapters(), [], None, [], {}, out)
|
||||
assert meta["title"] == "Test Story"
|
||||
assert meta["authors"] == ["Writer"]
|
||||
assert "Fantasy" in meta["tags"]
|
||||
|
||||
|
||||
def test_supported_sites():
|
||||
assert fff.is_supported_site("www.royalroad.com")
|
||||
assert fff.is_supported_site("WWW.RoyalRoad.com ")
|
||||
assert not fff.is_supported_site("example.com")
|
||||
|
||||
|
||||
def test_normalize_url():
|
||||
assert fff.normalize_url(URL) == ("https://www.royalroad.com/fiction/1234", "www.royalroad.com")
|
||||
assert fff.normalize_url("https://example.com/nothing") is None
|
||||
Reference in New Issue
Block a user