Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Die Zeit

Browse Source 
Merge branch 'update-zeitde-premium' of https://github.com/henninglosert/calibre
This commit is contained in:
Kovid Goyal 2015-04-17 09:05:14 +05:30
commit 82de189f1d
1 changed files with 12 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
recipes/zeitde_sub.recipe
View File

@ -25,7 +25,7 @@ class ZeitEPUBAbo(BasicNewsRecipe):
language = 'de' language = 'de'
lang = 'de-DE' lang = 'de-DE'
__author__ = 'Steffen Siebert, revised by Tobias Isenberg (with some code by Kovid Goyal)' __author__ = 'Steffen Siebert, revised by Tobias Isenberg (with some code by Kovid Goyal), updated by Henning Losert'
needs_subscription = True needs_subscription = True
conversion_options = { conversion_options = {
@ -117,18 +117,14 @@ class ZeitEPUBAbo(BasicNewsRecipe):
] ]
def build_index(self): def build_index(self):
domain = "https://premium.zeit.de" url = "https://meine.zeit.de/anmelden?url=https%3A//premium.zeit.de/node/125"
url = domain + "/abo/digitalpaket"
browser = self.get_browser() browser = self.get_browser()
# new login process # new login process
response = browser.open(url) browser.open(url)
# Get rid of nested form browser.select_form(nr=0)
response.set_data(response.get_data().replace('<div><form action="/abo/digitalpaket?destination=node%2F94" accept-charset="UTF-8" method="post" id="user-login-form" class="zol_inlinelabel">', '')) browser.form['email']=self.username
browser.set_response(response) browser.form['password']=self.password
browser.select_form(nr=2)
browser.form['name']=self.username
browser.form['pass']=self.password
browser.submit() browser.submit()
# now find the correct file, we will still use the ePub file # now find the correct file, we will still use the ePub file
epublink = browser.find_link(text_regex=re.compile('.*Download als Datei im ePub-Format für eReader.*')) epublink = browser.find_link(text_regex=re.compile('.*Download als Datei im ePub-Format für eReader.*'))
@ -176,22 +172,17 @@ class ZeitEPUBAbo(BasicNewsRecipe):
self.log.warning('Downloading cover') self.log.warning('Downloading cover')
try: try:
self.log.warning('Trying PDF-based cover') self.log.warning('Trying PDF-based cover')
domain = "https://premium.zeit.de" url = "https://meine.zeit.de/anmelden?url=https%3A//premium.zeit.de/node/125"
url = domain + "/abo/digitalpaket"
browser = self.get_browser() browser = self.get_browser()
# new login process # new login process
response=browser.open(url) browser.open(url)
# Get rid of nested form browser.select_form(nr=0)
response.set_data(response.get_data().replace('<div><form action="/abo/digitalpaket?destination=node%2F94" accept-charset="UTF-8" method="post" id="user-login-form" class="zol_inlinelabel">', '')) browser.form['email']=self.username
browser.set_response(response) browser.form['password']=self.password
browser.select_form(nr=2)
browser.form['name']=self.username
browser.form['pass']=self.password
browser.submit() browser.submit()
# actual cover search # actual cover search
pdflink = browser.find_link(url_regex=re.compile('system/files/epaper/DZ/pdf/DZ_ePaper*')) pdflink = browser.find_link(text_regex=re.compile('.*Download der gesamten Ausgabe als PDF Datei.*'))
cover_url = urlparse(pdflink.base_url)[0]+'://'+urlparse(pdflink.base_url)[1]+''+(urlparse(pdflink.url)[2]).replace('ePaper_','').replace('.pdf','_001.pdf') cover_url = urlparse(pdflink.base_url)[0]+'://'+urlparse(pdflink.base_url)[1]+''+(urlparse(pdflink.url)[2]).replace('ePaper_','').replace('.pdf','_001.pdf')
self.log.warning('PDF link found:') self.log.warning('PDF link found:')
self.log.warning(cover_url) self.log.warning(cover_url)