http -> https

This commit is contained in:
Kovid Goyal 2020-12-27 18:23:41 +05:30
parent ca6e78008d
commit d3ba0e98c5
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C

View File

@ -20,7 +20,7 @@ class Arcamax(BasicNewsRecipe):
use_embedded_content = False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
cover_url = 'http://www.arcamax.com/images/pub/amuse/leftcol/zits.jpg' cover_url = 'https://www.arcamax.com/images/pub/amuse/leftcol/zits.jpg'
# ###### USER PREFERENCES - SET COMICS AND NUMBER OF COMICS TO RETRIEVE ## # ###### USER PREFERENCES - SET COMICS AND NUMBER OF COMICS TO RETRIEVE ##
num_comics_to_get = 7 num_comics_to_get = 7
@ -41,41 +41,41 @@ class Arcamax(BasicNewsRecipe):
self.panel_counter = 0 self.panel_counter = 0
for title, url in [ for title, url in [
# ####### COMICS - GENERAL ######## # ####### COMICS - GENERAL ########
# (u"9 Chickweed Lane", u"http://www.arcamax.com/thefunnies/ninechickweedlane"), # (u"9 Chickweed Lane", u"https://www.arcamax.com/thefunnies/ninechickweedlane"),
# (u"Agnes", u"http://www.arcamax.com/thefunnies/agnes"), # (u"Agnes", u"https://www.arcamax.com/thefunnies/agnes"),
# (u"Andy Capp", u"http://www.arcamax.com/thefunnies/andycapp"), # (u"Andy Capp", u"https://www.arcamax.com/thefunnies/andycapp"),
(u"BC", u"http://www.arcamax.com/thefunnies/bc"), (u"BC", u"https://www.arcamax.com/thefunnies/bc"),
# (u"Baby Blues", u"http://www.arcamax.com/thefunnies/babyblues"), # (u"Baby Blues", u"https://www.arcamax.com/thefunnies/babyblues"),
# (u"Beetle Bailey", u"http://www.arcamax.com/thefunnies/beetlebailey"), # (u"Beetle Bailey", u"https://www.arcamax.com/thefunnies/beetlebailey"),
(u"Blondie", u"http://www.arcamax.com/thefunnies/blondie"), (u"Blondie", u"https://www.arcamax.com/thefunnies/blondie"),
# u"Boondocks", u"http://www.arcamax.com/thefunnies/boondocks"), # u"Boondocks", u"https://www.arcamax.com/thefunnies/boondocks"),
# (u"Cathy", u"http://www.arcamax.com/thefunnies/cathy"), # (u"Cathy", u"https://www.arcamax.com/thefunnies/cathy"),
# (u"Daddys Home", u"http://www.arcamax.com/thefunnies/daddyshome"), # (u"Daddys Home", u"https://www.arcamax.com/thefunnies/daddyshome"),
(u"Dilbert", u"http://www.arcamax.com/thefunnies/dilbert"), (u"Dilbert", u"https://www.arcamax.com/thefunnies/dilbert"),
# (u"Dinette Set", u"http://www.arcamax.com/thefunnies/thedinetteset"), # (u"Dinette Set", u"https://www.arcamax.com/thefunnies/thedinetteset"),
(u"Dog Eat Doug", u"http://www.arcamax.com/thefunnies/dogeatdoug"), (u"Dog Eat Doug", u"https://www.arcamax.com/thefunnies/dogeatdoug"),
(u"Doonesbury", u"http://www.arcamax.com/thefunnies/doonesbury"), # (u"Doonesbury", u"https://www.arcamax.com/thefunnies/doonesbury"),
# (u"Dustin", u"http://www.arcamax.com/thefunnies/dustin"), # (u"Dustin", u"https://www.arcamax.com/thefunnies/dustin"),
(u"Family Circus", u"http://www.arcamax.com/thefunnies/familycircus"), (u"Family Circus", u"https://www.arcamax.com/thefunnies/familycircus"),
(u"Garfield", u"http://www.arcamax.com/thefunnies/garfield"), (u"Garfield", u"https://www.arcamax.com/thefunnies/garfield"),
# (u"Get Fuzzy", u"http://www.arcamax.com/thefunnies/getfuzzy"), # (u"Get Fuzzy", u"https://www.arcamax.com/thefunnies/getfuzzy"),
# (u"Girls and Sports", u"http://www.arcamax.com/thefunnies/girlsandsports"), # (u"Girls and Sports", u"https://www.arcamax.com/thefunnies/girlsandsports"),
# (u"Hagar the Horrible", u"http://www.arcamax.com/thefunnies/hagarthehorrible"), # (u"Hagar the Horrible", u"https://www.arcamax.com/thefunnies/hagarthehorrible"),
# (u"Heathcliff", u"http://www.arcamax.com/thefunnies/heathcliff"), # (u"Heathcliff", u"https://www.arcamax.com/thefunnies/heathcliff"),
# (u"Jerry King Cartoons", u"http://www.arcamax.com/thefunnies/humorcartoon"), # (u"Jerry King Cartoons", u"https://www.arcamax.com/thefunnies/humorcartoon"),
# (u"Luann", u"http://www.arcamax.com/thefunnies/luann"), # (u"Luann", u"https://www.arcamax.com/thefunnies/luann"),
# (u"Momma", u"http://www.arcamax.com/thefunnies/momma"), # (u"Momma", u"https://www.arcamax.com/thefunnies/momma"),
# (u"Mother Goose and Grimm", u"http://www.arcamax.com/thefunnies/mothergooseandgrimm"), # (u"Mother Goose and Grimm", u"https://www.arcamax.com/thefunnies/mothergooseandgrimm"),
(u"Mutts", u"http://www.arcamax.com/thefunnies/mutts"), (u"Mutts", u"https://www.arcamax.com/thefunnies/mutts"),
# (u"Non Sequitur", u"http://www.arcamax.com/thefunnies/nonsequitur"), # (u"Non Sequitur", u"https://www.arcamax.com/thefunnies/nonsequitur"),
# (u"Pearls Before Swine", u"http://www.arcamax.com/thefunnies/pearlsbeforeswine"), # (u"Pearls Before Swine", u"https://www.arcamax.com/thefunnies/pearlsbeforeswine"),
# (u"Pickles", u"http://www.arcamax.com/thefunnies/pickles"), # (u"Pickles", u"https://www.arcamax.com/thefunnies/pickles"),
# (u"Red and Rover", u"http://www.arcamax.com/thefunnies/redandrover"), # (u"Red and Rover", u"https://www.arcamax.com/thefunnies/redandrover"),
# (u"Rubes", u"http://www.arcamax.com/thefunnies/rubes"), # (u"Rubes", u"https://www.arcamax.com/thefunnies/rubes"),
# (u"Rugrats", u"http://www.arcamax.com/thefunnies/rugrats"), # (u"Rugrats", u"https://www.arcamax.com/thefunnies/rugrats"),
(u"Speed Bump", u"http://www.arcamax.com/thefunnies/speedbump"), (u"Speed Bump", u"https://www.arcamax.com/thefunnies/speedbump"),
(u"Wizard of Id", u"http://www.arcamax.com/thefunnies/wizardofid"), (u"Wizard of Id", u"https://www.arcamax.com/thefunnies/wizardofid"),
(u"Zits", u"http://www.arcamax.com/thefunnies/zits"), (u"Zits", u"https://www.arcamax.com/thefunnies/zits"),
]: ]:
self.log('Finding strips for:', title) self.log('Finding strips for:', title)
articles = self.make_links(url, title) articles = self.make_links(url, title)
@ -98,7 +98,7 @@ class Arcamax(BasicNewsRecipe):
f.write(raw) f.write(raw)
soup = self.index_to_soup(raw) soup = self.index_to_soup(raw)
a = soup.find(name='a', attrs={'class': ['prev']}) a = soup.find(name='a', attrs={'class': ['prev']})
prev_page_url = 'http://www.arcamax.com' + a['href'] prev_page_url = 'https://www.arcamax.com' + a['href']
title = self.tag_to_string( title = self.tag_to_string(
soup.find('title')).partition('|')[0].strip() soup.find('title')).partition('|')[0].strip()
if 'for' not in title.split(): if 'for' not in title.split():
@ -117,7 +117,7 @@ class Arcamax(BasicNewsRecipe):
def preprocess_html(self, soup): def preprocess_html(self, soup):
for img in soup.findAll('img', src=True): for img in soup.findAll('img', src=True):
if img['src'].startswith('/'): if img['src'].startswith('/'):
img['src'] = 'http://arcamax.com' + img['src'] img['src'] = 'https://arcamax.com' + img['src']
return soup return soup
extra_css = ''' extra_css = '''