Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-31 14:33:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update world_archeology.recipe

Browse Source
This commit is contained in:
unkn0w7n 2025-07-11 18:21:20 +05:30
parent d52b832478
commit e86df5aca1
1 changed files with 21 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
recipes/world_archeology.recipe
View File

@ -26,24 +26,33 @@ class worldarch(BasicNewsRecipe):
simultaneous_downloads = 1
extra_css = '''
[class^="meta"] { font-size:small; }
[class^="meta"], [class~="__author__text"], [class~="__date"] { 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}),
dict(attrs={'class': lambda x: x and any(tag in x for tag in [
'__image', '__header', '__background',
'__body_area', '__author__text', '__date'
])})
]
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 any(cls in x.split()
for cls in ['avatar', 'what-mag-row'])}),
dict(attrs={'class':lambda x: x and '--share' in x})
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'src': True}):
if '?w=' in img['src']:
res = '?w=600'
w = self.recipe_specific_options.get('res')
if w and isinstance(w, str):
res = '?w=' + w
img['src'] = img['src'].split('?')[0] + res
exp = soup.find(attrs={'class':lambda x: x and 'post-subtitle' in x.split()})
if exp:
exp.name = 'p'
@ -53,7 +62,12 @@ class worldarch(BasicNewsRecipe):
'issue': {
'short': 'Enter the Issue Number you want to download ',
'long': 'For example, 136'
}
},
'res': {
'short': 'For hi-res images, select a resolution from the\nfollowing options: 800, 1000, 1200 or 1500',
'long': 'This is useful for non e-ink devices, and for a lower file size\nthan the default, use 400 or 300.',
'default': '600',
},
}
def parse_index(self):
@ -77,7 +91,7 @@ class worldarch(BasicNewsRecipe):
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']
self.cover_url = cov.img['src'].split('?')[0] + '?w=600'
div = issue.find('div', attrs={'class':lambda x: x and 'entry-content' in x.split()})
feeds = []