From 17b6b6ad5e7e4fee861160554334ea3c38f8cb03 Mon Sep 17 00:00:00 2001
From: unkn0w7n <51942695+unkn0w7n@users.noreply.github.com>
Date: Sun, 7 Jul 2024 10:30:54 +0530
Subject: [PATCH] Minerva Magazine

---
 recipes/icons/minerva_magazine.png | Bin 0 -> 380 bytes
 recipes/military_history.recipe    |   5 +-
 recipes/minerva_magazine.recipe    | 102 +++++++++++++++++++++++++++++
 recipes/world_archeology.recipe    |   5 +-
 4 files changed, 110 insertions(+), 2 deletions(-)
 create mode 100644 recipes/icons/minerva_magazine.png
 create mode 100644 recipes/minerva_magazine.recipe

diff --git a/recipes/icons/minerva_magazine.png b/recipes/icons/minerva_magazine.png
new file mode 100644
index 0000000000000000000000000000000000000000..57be82fff8cc3ca7ec3db328df00d75a65d66d55
GIT binary patch
literal 380
zcmV-?0fYXDP)<h;3K|Lk000e1NJLTq000mG000mO1^@s6AM^iV0003)Nkl<ZIE}56
zF^a-K6ox;|&Iq}JiD|rmg;?wzJV2137m;nYwD15^#YPVi8;e+4i3BXfkSc;8h!(S3
zY+P3o7j*Z*z~k}$kN<xRKp!{(9}m70&@W|;<heSRGTPHszBHC)F&GS3uh%phjohMb
z+eA^sa5$t^tK|XP?Uo=2NYj*Fua^Tfn@w!nCI|vHn@t`7ptVLRh3mRhDwRUZTI=En
zmzqo_NGWNz+uyTRtHpdiF9hZQhr@yKczhGXvMk~_E(E+34V6;NW;3eQD!bi|<MCK1
zz6%J$kmYiT=Xop^3#QZQT|h3vPZ!;87t=I<b#Ma^LLh_yU^E)xI1WjYT$jsb48ynq
z7{D8R9m;iG>h(HN6p^MWLI`}{M@mVj)4_2ZwAQRvEB5<60RQrp&wtRLjSTXd#d$~!
aynh02pnAR?^oF$n0000<MNUMnLSTXwSf8!{

literal 0
HcmV?d00001

diff --git a/recipes/military_history.recipe b/recipes/military_history.recipe
index 3f6565e611..1de04fb46c 100644
--- a/recipes/military_history.recipe
+++ b/recipes/military_history.recipe
@@ -5,7 +5,7 @@ from calibre import browser
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class milthist(BasicNewsRecipe):
-    title = 'Military History Matters'
+    title = 'The Past: Military History Matters'
     language = 'en'
     __author__ = 'unkn0wn'
     description = (
@@ -53,6 +53,9 @@ class milthist(BasicNewsRecipe):
         # url = ''
 
         issue = self.index_to_soup(url)
+        ti = issue.find('h1', attrs={'class':lambda x: x and 'post-title' in x.split()})
+        if ti:
+            self.title = self.tag_to_string(ti).strip()
         dt = soup.find(attrs={'class':lambda x: x and '__date' in x})
         if dt:
             self.timefmt = ' [' + self.tag_to_string(dt).strip() + ']'
diff --git a/recipes/minerva_magazine.recipe b/recipes/minerva_magazine.recipe
new file mode 100644
index 0000000000..181d5c88f9
--- /dev/null
+++ b/recipes/minerva_magazine.recipe
@@ -0,0 +1,102 @@
+'''
+https://minervamagazine.com/
+'''
+from calibre import browser
+from calibre.web.feeds.news import BasicNewsRecipe
+
+
+class minerva(BasicNewsRecipe):
+    title = 'The Past: Minerva Magazine'
+    language = 'en'
+    __author__ = 'unkn0wn'
+    description = (
+        'Minerva, Archaeology and Ancient art, was a bi-monthly magazine publishing features on exhibitions, excavations, '
+        'and museums, interviews, news items, and book reviews. It ran from 1990 to 2023. So use this recipe to fetch past issues.'
+    )
+    no_stylesheets = True
+    use_embedded_content = False
+    remove_attributes = ['style', 'height', 'width']
+    ignore_duplicate_articles = {'url'}
+    resolve_internal_links = True
+    masthead_url = 'https://minervamagazine.com/media/website/Minerva-mastheadandstrap-black_323x80.png'
+    simultaneous_downloads = 1
+
+    extra_css = '''
+        [class^="meta"] { font-size:small; }
+        .post-subtitle { font-style: italic; color:#202020; }
+        .wp-block-image { font-size:small; text-align:center; }
+    '''
+
+    keep_only_tags = [
+        dict(attrs={'class':lambda x: x and '__header' in x}),
+        dict(attrs={'class':lambda x: x and '__background' in x}),
+        dict(attrs={'class':lambda x: x and '__body_area' in x}),
+    ]
+
+    remove_tags = [
+        dict(attrs={'class':'ad-break'}),
+        dict(attrs={'class':lambda x: x and 'avatar' in x.split()}),
+        dict(attrs={'class':lambda x: x and '--share' in x})
+    ]
+
+    def preprocess_html(self, soup):
+        exp = soup.find(attrs={'class':lambda x: x and 'post-subtitle' in x.split()})
+        if exp:
+            exp.name = 'p'
+        return soup
+
+    def parse_index(self):
+        soup = self.index_to_soup('https://the-past.com/category/magazines/minerva/')
+        art = soup.find('article', attrs={'class':lambda x: x and 'tag-magazines' in x.split()})
+        url = art.h2.a['href']
+
+        # for past editions, add url
+        # url = ''
+
+        issue = self.index_to_soup(url)
+        ti = issue.find('h1', attrs={'class':lambda x: x and 'post-title' in x.split()})
+        if ti:
+            self.title = self.tag_to_string(ti).strip()
+        dt = soup.find(attrs={'class':lambda x: x and '__date' in x})
+        if dt:
+            self.timefmt = ' [' + self.tag_to_string(dt).strip() + ']'
+        edit = issue.find('h2', attrs={'id':'from-the-editor'})
+        if edit and edit.findParent('div'):
+            self.description = self.tag_to_string(edit.findParent('div'))
+        cov = issue.find('figure', attrs={'class':lambda x: x and 'wp-block-image' in x.split()})
+        if cov:
+            self.cover_url = cov.img['src']
+        div = issue.find('div', attrs={'class':lambda x: x and 'entry-content' in x.split()})
+
+        feeds = []
+
+        h2 = div.findAll('h2', attrs={'class':lambda x: x and 'wp-block-heading' in x.split()})
+        lt = div.findAll(attrs={'class':'display-posts-listing'})
+        for x, y in zip(h2, lt):
+            section = self.tag_to_string(x).strip()
+            self.log(section)
+            articles = []
+            for a in y.findAll('a', href=True, attrs={'class':'title'}):
+                url = a['href']
+                title = self.tag_to_string(a).strip()
+                desc = ''
+                exp = a.findNext(attrs={'class':'excerpt'})
+                if exp:
+                    desc = self.tag_to_string(exp).strip()
+                self.log('\t', title, '\n\t', desc, '\n\t\t', url)
+                articles.append({'title': title, 'description':desc, 'url': url})
+            if articles:
+                feeds.append((section, articles))
+        return feeds
+
+    def get_browser(self, *args, **kwargs):
+        return self
+
+    def clone_browser(self, *args, **kwargs):
+        return self.get_browser()
+
+    def open_novisit(self, *args, **kwargs):
+        br = browser()
+        return br.open_novisit(*args, **kwargs)
+
+    open = open_novisit
diff --git a/recipes/world_archeology.recipe b/recipes/world_archeology.recipe
index 9a17b1e75a..fe74c87357 100644
--- a/recipes/world_archeology.recipe
+++ b/recipes/world_archeology.recipe
@@ -5,7 +5,7 @@ from calibre import browser
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class worldarch(BasicNewsRecipe):
-    title = 'Current World Archaeology'
+    title = 'The Past: Current World Archaeology'
     language = 'en'
     __author__ = 'unkn0wn'
     description = (
@@ -55,6 +55,9 @@ class worldarch(BasicNewsRecipe):
         # url = ''
 
         issue = self.index_to_soup(url)
+        ti = issue.find('h1', attrs={'class':lambda x: x and 'post-title' in x.split()})
+        if ti:
+            self.title = self.tag_to_string(ti).strip()
         dt = soup.find(attrs={'class':lambda x: x and '__date' in x})
         if dt:
             self.timefmt = ' [' + self.tag_to_string(dt).strip() + ']'