From 41cbe3640eeeffed6d3832b1449e9e3e68545691 Mon Sep 17 00:00:00 2001
From: Michel Roux <xefir@crystalyx.net>
Date: Sun, 5 Mar 2023 16:18:01 +0100
Subject: [PATCH] Adapt for the rewrite of book 1

---
 books.py    | 22 +++++++++++++++-------
 poetry.lock |  6 +++---
 2 files changed, 18 insertions(+), 10 deletions(-)

diff --git a/books.py b/books.py
index 25cc0a7..8c8760d 100644
--- a/books.py
+++ b/books.py
@@ -82,7 +82,7 @@ def async_wrap(func):
 
 makedirs(name=OUTPUT_DIR, exist_ok=True)
 cover_req = get(
-    url="https://i0.wp.com/thefantasyinn.com/wp-content/uploads/2018/08/twi.jpg",
+    url="https://i0.wp.com/wanderinginn.com/wp-content/uploads/2023/03/Wandering_Inn-Vol1-eCover.jpg",  # noqa: E501
     stream=True,
 )
 Image.open(cover_req.raw).save(f"{OUTPUT_DIR}/cover.png")
@@ -94,17 +94,19 @@ def process_volume(epub: Epub, urls: List[str]):
         page_html = BeautifulSoup(markup=page_req.text, features="lxml")
         page_content = page_html.select_one("div.entry-content")
         page_title = page_html.select_one("h1.entry-title")
-        page_date = page_html.find(name="meta", property="article:modified_time")
 
-        if not page_content or not page_title or type(page_date) is not Tag:
-            raise Exception()
+        if not page_content or not page_title:
+            raise Exception("Missing title or content")
+
+        title = page_title.get_text().strip()
+        if not title:
+            continue
 
         galleries = page_content.select("div.tiled-gallery")
 
         for gallery in galleries:
             gallery.decompose()
 
-        title = page_title.get_text().strip()
         chapter = create_chapter_from_string(
             html=page_content.prettify(),
             title=title,
@@ -118,7 +120,9 @@ def process_volume(epub: Epub, urls: List[str]):
 
 
 @async_wrap
-def process_book(url: str, creator: str, publisher: str, language: str):
+def process_book(
+    url: str, creator: str, publisher: str, language: str, strip_first=False
+):
     toc_req = get(url)
     toc_html = BeautifulSoup(markup=toc_req.text, features="lxml")
     toc_content = toc_html.select("div.entry-content > p")
@@ -127,10 +131,13 @@ def process_book(url: str, creator: str, publisher: str, language: str):
 
     if not toc_title or type(toc_date) is not Tag:
         raise Exception("Missing title or date")
+    title = toc_title.get_text().strip()
+
+    if strip_first:
+        toc_content.pop(0)
 
     for i, toc_line in enumerate(toc_content):
         if i % 2 == 0:
-            title = toc_title.get_text().strip()
             volume = toc_line.get_text().strip()
         elif volume:
             epub = Epub(
@@ -163,6 +170,7 @@ async def create_books():
             creator="Pirateaba",
             publisher="Xefir",
             language="en",
+            strip_first=True,
         ),
     )
 
diff --git a/poetry.lock b/poetry.lock
index 1fdbb70..36ddcae 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -630,14 +630,14 @@ tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "pa
 
 [[package]]
 name = "platformdirs"
-version = "3.0.0"
+version = "3.1.0"
 description = "A small Python package for determining appropriate platform-specific dirs, e.g. a \"user data dir\"."
 category = "dev"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "platformdirs-3.0.0-py3-none-any.whl", hash = "sha256:b1d5eb14f221506f50d6604a561f4c5786d9e80355219694a1b244bcd96f4567"},
-    {file = "platformdirs-3.0.0.tar.gz", hash = "sha256:8a1228abb1ef82d788f74139988b137e78692984ec7b08eaa6c65f1723af28f9"},
+    {file = "platformdirs-3.1.0-py3-none-any.whl", hash = "sha256:13b08a53ed71021350c9e300d4ea8668438fb0046ab3937ac9a29913a1a1350a"},
+    {file = "platformdirs-3.1.0.tar.gz", hash = "sha256:accc3665857288317f32c7bebb5a8e482ba717b474f3fc1d18ca7f9214be0cef"},
 ]
 
 [package.extras]