Merge branch 'master' of https://github.com/unkn0w7n/calibre

recipes/ancient_egypt.recipe

@@ -0,0 +1,102 @@
+'''
+https://ancientegyptmagazine.com
+'''
+from calibre import browser
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class ancientegypt(BasicNewsRecipe):
+    title = 'The Past: Ancient Egypt Magazine'
+    language = 'en'
+    __author__ = 'unkn0wn'
+    description = (
+        'Ancient Egypt is the world\'s leading Egyptology magazine, exploring the history, people and culture of the Nile Valley. '
+        'Now in a larger format with a fresh new design, AE brings you the latest news and discoveries, and feature articles covering '
+        'more than 5000 years of Egyptian history. Published bimonthly.'
+    )
+    no_stylesheets = True
+    use_embedded_content = False
+    remove_attributes = ['style', 'height', 'width']
+    ignore_duplicate_articles = {'url'}
+    resolve_internal_links = True
+    masthead_url = 'https://ancientegyptmagazine.com/media/website/ae-logo-2.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/ae/')
+        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

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 = (
@@ -53,14 +53,18 @@ 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() + ']'
         edit = issue.find('h2', attrs={'id':'from-the-editor'})
-        if edit.findNext('p'):
-            self.description = self.tag_to_string(edit.findNext('p'))
-        if edit.findPrevious('figure'):
-            self.cover_url = edit.findPrevious('figure').img['src']
+        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 = []

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

recipes/world_archeology.recipe

@@ -0,0 +1,103 @@
+'''
+https://www.world-archaeology.com
+'''
+from calibre import browser
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class worldarch(BasicNewsRecipe):
+    title = 'The Past: Current World Archaeology'
+    language = 'en'
+    __author__ = 'unkn0wn'
+    description = (
+        'Travel the globe with Current World Archaeology, the magazine that brings you up-to-date with the latest archaeological discoveries. '
+        'Explore sites – and sights – through our exclusive features and eye-popping photography. We bring you the stories from the '
+        'archaeologists themselves, so you learn first-hand from the experts about the latest finds and most up-to-date research. '
+        'Published six times a year.'
+    )
+    no_stylesheets = True
+    use_embedded_content = False
+    remove_attributes = ['style', 'height', 'width']
+    ignore_duplicate_articles = {'url'}
+    resolve_internal_links = True
+    masthead_url = 'https://i0.wp.com/www.world-archaeology.com/wp-content/uploads/2016/02/cwa-logo.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/cwa/')
+        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