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

recipes/economist.recipe

@@ -232,21 +232,20 @@ class Economist(BasicNewsRecipe):
     if use_archive:
         def parse_index(self):
             # return self.economist_test_article()
-            url = 'https://www.economist.com/weeklyedition/archive'
+            # url = 'https://www.economist.com/weeklyedition/archive'
-            if edition_date:
-                url = 'https://www.economist.com/weeklyedition/' + edition_date
-            soup = self.index_to_soup(url)
-            script_tag = soup.find("script", id="__NEXT_DATA__")
-            if script_tag is None:
-                raise ValueError('No script tag with JSON data found in the weeklyedition archive')
-            data = json.loads(script_tag.string)
-            content_id = data['props']['pageProps']['content']['id'].split('/')[-1]
             query = {
                 'query': 'query LatestWeeklyAutoEditionQuery($ref:String!){canonical(ref:$ref){hasPart(from:0 size:1 sort:"datePublished:desc"){parts{...WeeklyEditionFragment __typename}__typename}__typename}}fragment WeeklyEditionFragment on Content{id type datePublished image{...ImageCoverFragment __typename}url{canonical __typename}hasPart(size:100 sort:"publication.context.position"){parts{...ArticleFragment __typename}__typename}__typename}fragment ArticleFragment on Content{ad{grapeshot{channels{name __typename}__typename}__typename}articleSection{internal{id title:headline __typename}__typename}audio{main{id duration(format:"seconds")source:channel{id __typename}url{canonical __typename}__typename}__typename}byline dateline dateModified datePublished dateRevised flyTitle:subheadline id image{...ImageInlineFragment ...ImageMainFragment ...ImagePromoFragment __typename}print{title:headline flyTitle:subheadline rubric:description section{id title:headline __typename}__typename}publication{id tegID title:headline flyTitle:subheadline datePublished regionsAllowed url{canonical __typename}__typename}rubric:description source:channel{id __typename}tegID text(format:"json")title:headline type url{canonical __typename}topic contentIdentity{forceAppWebview mediaType articleType __typename}__typename}fragment ImageInlineFragment on Media{inline{url{canonical __typename}width height __typename}__typename}fragment ImageMainFragment on Media{main{url{canonical __typename}width height __typename}__typename}fragment ImagePromoFragment on Media{promo{url{canonical __typename}id width height __typename}__typename}fragment ImageCoverFragment on Media{cover{headline width height url{canonical __typename}regionsAllowed __typename}__typename}',  # noqa
                 'operationName': 'LatestWeeklyAutoEditionQuery',
-                'variables': '{{"ref":"/content/{}"}}'.format(content_id),
+                'variables': '{"ref":"/content/d06tg8j85rifiq3oo544c6b9j61dno2n"}',
             }
             if edition_date:
+                url = 'https://www.economist.com/weeklyedition/' + edition_date
+                soup = self.index_to_soup(url)
+                script_tag = soup.find("script", id="__NEXT_DATA__")
+                if script_tag is None:
+                    raise ValueError('No script tag with JSON data found in the weeklyedition archive')
+                data = json.loads(script_tag.string)
+                content_id = data['props']['pageProps']['content']['id'].split('/')[-1]
                 query = {
                     'query': 'query SpecificWeeklyEditionQuery($path:String!){section:canonical(ref:$path){...WeeklyEditionFragment __typename}}fragment WeeklyEditionFragment on Content{id type datePublished image{...ImageCoverFragment __typename}url{canonical __typename}hasPart(size:100 sort:"publication.context.position"){parts{...ArticleFragment __typename}__typename}__typename}fragment ArticleFragment on Content{ad{grapeshot{channels{name __typename}__typename}__typename}articleSection{internal{id title:headline __typename}__typename}audio{main{id duration(format:"seconds")source:channel{id __typename}url{canonical __typename}__typename}__typename}byline dateline dateModified datePublished dateRevised flyTitle:subheadline id image{...ImageInlineFragment ...ImageMainFragment ...ImagePromoFragment __typename}print{title:headline flyTitle:subheadline rubric:description section{id title:headline __typename}__typename}publication{id tegID title:headline flyTitle:subheadline datePublished regionsAllowed url{canonical __typename}__typename}rubric:description source:channel{id __typename}tegID text(format:"json")title:headline type url{canonical __typename}topic contentIdentity{forceAppWebview mediaType articleType __typename}__typename}fragment ImageInlineFragment on Media{inline{url{canonical __typename}width height __typename}__typename}fragment ImageMainFragment on Media{main{url{canonical __typename}width height __typename}__typename}fragment ImagePromoFragment on Media{promo{url{canonical __typename}id width height __typename}__typename}fragment ImageCoverFragment on Media{cover{headline width height url{canonical __typename}regionsAllowed __typename}__typename}',  # noqa
                     'operationName': 'SpecificWeeklyEditionQuery',

recipes/economist_free.recipe

@@ -232,21 +232,20 @@ class Economist(BasicNewsRecipe):
     if use_archive:
         def parse_index(self):
             # return self.economist_test_article()
-            url = 'https://www.economist.com/weeklyedition/archive'
+            # url = 'https://www.economist.com/weeklyedition/archive'
-            if edition_date:
-                url = 'https://www.economist.com/weeklyedition/' + edition_date
-            soup = self.index_to_soup(url)
-            script_tag = soup.find("script", id="__NEXT_DATA__")
-            if script_tag is None:
-                raise ValueError('No script tag with JSON data found in the weeklyedition archive')
-            data = json.loads(script_tag.string)
-            content_id = data['props']['pageProps']['content']['id'].split('/')[-1]
             query = {
                 'query': 'query LatestWeeklyAutoEditionQuery($ref:String!){canonical(ref:$ref){hasPart(from:0 size:1 sort:"datePublished:desc"){parts{...WeeklyEditionFragment __typename}__typename}__typename}}fragment WeeklyEditionFragment on Content{id type datePublished image{...ImageCoverFragment __typename}url{canonical __typename}hasPart(size:100 sort:"publication.context.position"){parts{...ArticleFragment __typename}__typename}__typename}fragment ArticleFragment on Content{ad{grapeshot{channels{name __typename}__typename}__typename}articleSection{internal{id title:headline __typename}__typename}audio{main{id duration(format:"seconds")source:channel{id __typename}url{canonical __typename}__typename}__typename}byline dateline dateModified datePublished dateRevised flyTitle:subheadline id image{...ImageInlineFragment ...ImageMainFragment ...ImagePromoFragment __typename}print{title:headline flyTitle:subheadline rubric:description section{id title:headline __typename}__typename}publication{id tegID title:headline flyTitle:subheadline datePublished regionsAllowed url{canonical __typename}__typename}rubric:description source:channel{id __typename}tegID text(format:"json")title:headline type url{canonical __typename}topic contentIdentity{forceAppWebview mediaType articleType __typename}__typename}fragment ImageInlineFragment on Media{inline{url{canonical __typename}width height __typename}__typename}fragment ImageMainFragment on Media{main{url{canonical __typename}width height __typename}__typename}fragment ImagePromoFragment on Media{promo{url{canonical __typename}id width height __typename}__typename}fragment ImageCoverFragment on Media{cover{headline width height url{canonical __typename}regionsAllowed __typename}__typename}',  # noqa
                 'operationName': 'LatestWeeklyAutoEditionQuery',
-                'variables': '{{"ref":"/content/{}"}}'.format(content_id),
+                'variables': '{"ref":"/content/d06tg8j85rifiq3oo544c6b9j61dno2n"}',
             }
             if edition_date:
+                url = 'https://www.economist.com/weeklyedition/' + edition_date
+                soup = self.index_to_soup(url)
+                script_tag = soup.find("script", id="__NEXT_DATA__")
+                if script_tag is None:
+                    raise ValueError('No script tag with JSON data found in the weeklyedition archive')
+                data = json.loads(script_tag.string)
+                content_id = data['props']['pageProps']['content']['id'].split('/')[-1]
                 query = {
                     'query': 'query SpecificWeeklyEditionQuery($path:String!){section:canonical(ref:$path){...WeeklyEditionFragment __typename}}fragment WeeklyEditionFragment on Content{id type datePublished image{...ImageCoverFragment __typename}url{canonical __typename}hasPart(size:100 sort:"publication.context.position"){parts{...ArticleFragment __typename}__typename}__typename}fragment ArticleFragment on Content{ad{grapeshot{channels{name __typename}__typename}__typename}articleSection{internal{id title:headline __typename}__typename}audio{main{id duration(format:"seconds")source:channel{id __typename}url{canonical __typename}__typename}__typename}byline dateline dateModified datePublished dateRevised flyTitle:subheadline id image{...ImageInlineFragment ...ImageMainFragment ...ImagePromoFragment __typename}print{title:headline flyTitle:subheadline rubric:description section{id title:headline __typename}__typename}publication{id tegID title:headline flyTitle:subheadline datePublished regionsAllowed url{canonical __typename}__typename}rubric:description source:channel{id __typename}tegID text(format:"json")title:headline type url{canonical __typename}topic contentIdentity{forceAppWebview mediaType articleType __typename}__typename}fragment ImageInlineFragment on Media{inline{url{canonical __typename}width height __typename}__typename}fragment ImageMainFragment on Media{main{url{canonical __typename}width height __typename}__typename}fragment ImagePromoFragment on Media{promo{url{canonical __typename}id width height __typename}__typename}fragment ImageCoverFragment on Media{cover{headline width height url{canonical __typename}regionsAllowed __typename}__typename}',  # noqa
                     'operationName': 'SpecificWeeklyEditionQuery',

recipes/natgeo.recipe

@@ -106,7 +106,7 @@ def parse_article(edg):
     yield '<h1>' + escape(sc['sclTtl']) + '</h1>'
     yield '<div class="byline">' + escape(sc['sclDsc']) + '</div>'
     yield '<p>'
-    for line in parse_contributors(edg['cntrbGrp']):
+    for line in parse_contributors(edg.get('cntrbGrp', {})):
         yield line
     ts = parse_iso8601(edg['mdDt'], as_utc=False).strftime('%B %d, %Y')
     yield '<div class="time">Published: ' + escape(ts) + '</div>'

recipes/natgeohis.recipe

@@ -105,7 +105,7 @@ def parse_article(edg):
     yield '<h1>' + escape(sc['sclTtl']) + '</h1>'
     yield '<div class="byline">' + escape(sc['sclDsc']) + '</div>'
     yield '<p>'
-    for line in parse_contributors(edg['cntrbGrp']):
+    for line in parse_contributors(edg.get('cntrbGrp', {})):
         yield line
     ts = parse_iso8601(edg['mdDt'], as_utc=False).strftime('%B %d, %Y')
     yield '<div class="time">Published: ' + escape(ts) + '</div>'

recipes/natgeomag.recipe

@@ -110,7 +110,7 @@ def parse_article(edg):
     yield '<h1>' + escape(sc['sclTtl']) + '</h1>'
     yield '<div class="byline">' + escape(sc['sclDsc']) + '</div>'
     yield '<p>'
-    for line in parse_contributors(edg['cntrbGrp']):
+    for line in parse_contributors(edg.get('cntrbGrp', {})):
         yield line
     ts = parse_iso8601(edg['mdDt'], as_utc=False).strftime('%B %d, %Y')
     yield '<div class="time">Published: ' + escape(ts) + '</div>'
@@ -187,14 +187,20 @@ class NatGeo(BasicNewsRecipe):
         name = soup.find(attrs={'class':lambda x: x and 'Header__Description' in x.split()})
         self.title = 'National Geographic ' + self.tag_to_string(name)
         ans = {}
-        ans2 = None
         if photoart := soup.find(attrs={'class':lambda x: x and 'BgImagePromo__Container__Text__Link' in x.split()}):
-            ans2 = []
+            section = 'Photo Essay'
             title = self.tag_to_string(photoart)
             url = photoart['href']
             if url.startswith('/'):
                 url = 'https://www.nationalgeographic.com' + url
-            ans2.append(('Photo Essay', [{'title': title, 'url': url}]))
+            articles = ans.setdefault(section, [])
+            articles.append({'title': title, 'url': url})
+        for promo in soup.findAll(**classes('OneUpPromoCard__Content')):
+            url = promo.a['href']
+            section = self.tag_to_string(promo.find(**classes('SectionLabel')))
+            title = self.tag_to_string(promo.find(**classes('Card__Content__Heading')))
+            articles = ans.setdefault(section, [])
+            articles.append({'title': title, 'url': url})
         for gird in soup.findAll(attrs={'class':'GridPromoTile'}):
             for article in soup.findAll('article'):
                 a = article.find('a')
@@ -208,8 +214,6 @@ class NatGeo(BasicNewsRecipe):
                 articles = ans.setdefault(section, [])
                 articles.append({'title': title, 'url': url})
             self.log(pformat(ans))
-            if ans2:
-                return list(ans.items()) + ans2
             return list(ans.items())
 
     def preprocess_raw_html(self, raw_html, url):