This commit is contained in:
unkn0w7n 2024-11-19 21:43:34 +05:30
parent 3b0fcaf924
commit 55e1928bd6

View File

@ -263,7 +263,7 @@ class Economist(BasicNewsRecipe):
for x in data:
if ed_date in x['datePublished']:
return x['id']
raise ValueError(ed_date, ' not found.')
return None
def parse_index(self):
edition_date = self.recipe_specific_options.get('date')
@ -276,13 +276,17 @@ class Economist(BasicNewsRecipe):
}
if edition_date and isinstance(edition_date, str):
content_id = self.get_content_id(edition_date)
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{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 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}__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',
'variables': '{{"path":"{}"}}'.format(content_id),
}
if content_id:
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{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 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}__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',
'variables': '{{"path":"{}"}}'.format(content_id),
}
url = 'https://cp2-graphql-gateway.p.aws.economist.com/graphql?' + urlencode(query, safe='()!', quote_via=quote)
try:
if edition_date and isinstance(edition_date, str):
if not content_id:
raise ValueError(edition_date, ' not found, trying web edition')
raw = self.index_to_soup(url, raw=True)
except Exception:
self.log('Fetching articles from web archive.')