From c8e8759594680394530d22b490ae39b92cf445a2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Constantin=20Mu=CC=88ller?= Date: Tue, 16 Jan 2018 22:44:02 +0100 Subject: [PATCH 1/8] updated web__heute_de --- services/web__heute_de.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/services/web__heute_de.py b/services/web__heute_de.py index bb39875..1d59bc7 100644 --- a/services/web__heute_de.py +++ b/services/web__heute_de.py @@ -1,9 +1,9 @@ refresh = 300 -version = 20161106.01 +version = 20180116.01 -urls = ['http://www.heute.de/'] -regex = [r'https?:\/\/[^\/]*heute\.de'] +urls = ['http://www.heute.de/','https://www.zdf.de/nachrichten/'] +regex = [r'https?:\/\/[^\/]*heute\.de',r'https?:\/\/[^\/]*zdf\.de'] videoregex = [] liveregex = [] - +wikidata = 'Q48989' From e99ea5f3f8ae8df2978baa2f27fae29838b85977 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Constantin=20Mu=CC=88ller?= Date: Tue, 16 Jan 2018 23:23:50 +0100 Subject: [PATCH 2/8] updated web__dw_com added all languages (not all languages have full rss feeds) --- services/web__dw_com.py | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) diff --git a/services/web__dw_com.py b/services/web__dw_com.py index 365d7e5..c956800 100644 --- a/services/web__dw_com.py +++ b/services/web__dw_com.py @@ -1,12 +1,41 @@ refresh = 7200 -version = 20161106.01 +version = 20180116.01 urls = ['http://www.dw.com/en/top-stories/s-9097', + 'http://www.dw.com/de/themen/s-9077', 'http://rss.dw.com/rdf/rss-en-all', 'http://rss.dw.com/rdf/rss-de-all', + 'http://rss.dw.com/rdf/rss-alb-all', + 'http://www.dw.com/am/%E1%8B%AD%E1%8B%98%E1%89%B5/s-11646', + 'http://rss.dw.de/rdf/rss-ar-all', + 'http://www.dw.com/bn/%E0%A6%AC%E0%A6%BF%E0%A6%B7%E0%A7%9F/s-11929', + 'http://rss.dw-world.de/rdf/rss-bos-all', + 'http://www.dw.com/bg/%D0%BD%D0%B0%D1%87%D0%B0%D0%BB%D0%BE/s-10257', + 'http://partner.dw.com/rdf/rss-chi-all', + 'http://partner.dw.com/rdf/rss-cro-all', + 'http://rss.dw.com/rdf/rss-dar-all', + 'http://rss.dw.com/rdf/rss-fre-all', + 'http://www.dw.com/el/%CE%B8%CE%B5%CE%BC%CE%B1%CF%84%CE%B1/s-10507', + 'http://www.dw.com/ha/batutuwa/s-11603', + 'http://www.dw.com/hi/%E0%A4%96%E0%A4%AC%E0%A4%B0%E0%A5%87%E0%A4%82/s-11931', + 'http://rss.dw.com/rdf/rss-ind-all', + 'http://www.dw.com/sw/idhaa-ya-kiswahili/s-11588', + 'http://www.dw.com/mk/%D1%82%D0%B5%D0%BC%D0%B8/s-10339', + 'http://www.dw.com/ps/%D8%AF%D9%88%D9%8A%DA%86%D9%87-%D9%88%D9%8A%D9%84%D9%87-%D9%BE%DA%9A%D8%AA%D9%88/s-11722', + 'http://rss.dw.com/rdf/rss-per-all', + 'http://partner.dw.com/xml/rss-pol-all', + 'http://www.dw.com/pt-002/not%C3%ADcias/s-13918', + 'http://www.dw.com/pt-br/not%C3%ADcias/s-7111', + 'http://www.dw.com/ro/focus/s-10575', + 'http://rss.dw.de/xml/rss-ru-all', + 'http://rss.dw.com/rdf/serbian_all', + 'http://www.dw.com/es/actualidad/s-30684', + 'http://partner.dw.com/rdf/rss-tur-all', + 'http://rss.dw.com/rdf/rss-ukr-all', + 'http://www.dw.com/ur/%D8%B9%D9%86%D9%88%D8%A7%D9%86%D8%A7%D8%AA/s-11933', 'http://www.dw.com/en/media-center/all-media-content/s-100826'] regex = [r'^https?:\/\/[^\/]*dw\.com\/'] videoregex = [r'\/av-'] liveregex = [] - +wikidata = 'Q153770' From e28914efef5990a2c5ba4cb24e63206c867d60c2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Constantin=20Mu=CC=88ller?= Date: Tue, 16 Jan 2018 23:40:19 +0100 Subject: [PATCH 3/8] added Wikidata IDs --- services/web__deutschlandradio_de.py | 3 +-- services/web__spiegel_de.py | 1 + services/web__tagesschau_de.py | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/services/web__deutschlandradio_de.py b/services/web__deutschlandradio_de.py index 1463b18..7995506 100644 --- a/services/web__deutschlandradio_de.py +++ b/services/web__deutschlandradio_de.py @@ -6,5 +6,4 @@ regex = [r'https?:\/\/[^\/]*deutschland', r'https?:\/\/[^\/]*dradio\.de'] videoregex = [r'audio', r'video'] liveregex = [] - - +wikidata = 'Q702314' diff --git a/services/web__spiegel_de.py b/services/web__spiegel_de.py index f240ee9..3fba7d8 100644 --- a/services/web__spiegel_de.py +++ b/services/web__spiegel_de.py @@ -28,3 +28,4 @@ regex = [r'^http?:\/\/[^\/]*spiegel\.de\/'] videoregex = [r'/video/'] liveregex = [] +wikidata = 'Q278151' diff --git a/services/web__tagesschau_de.py b/services/web__tagesschau_de.py index 6bf6629..60da2e9 100644 --- a/services/web__tagesschau_de.py +++ b/services/web__tagesschau_de.py @@ -7,5 +7,5 @@ regex = [r'https?:\/\/[^\/]*tagesschau\.de'] videoregex = [r'video', r'\/multimedia\/', r'audio'] liveregex = [] - +wikidata = 'Q1409067' From fab115010cb6837f1284146859a2303fa18eb7bf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Constantin=20Mu=CC=88ller?= Date: Wed, 17 Jan 2018 00:47:38 +0100 Subject: [PATCH 4/8] added german news sites from issue #6 --- services/web__faz_net.py | 9 +++++++++ services/web__focus_de.py | 9 +++++++++ services/web__stern_de.py | 9 +++++++++ services/web__sueddeutsche_de.py | 9 +++++++++ services/web__tagesspiegel_de.py | 9 +++++++++ services/web__taz_de.py | 9 +++++++++ services/web__welt_de.py | 9 +++++++++ services/web__zeit_de.py | 9 +++++++++ 8 files changed, 72 insertions(+) create mode 100644 services/web__faz_net.py create mode 100644 services/web__focus_de.py create mode 100644 services/web__stern_de.py create mode 100644 services/web__sueddeutsche_de.py create mode 100644 services/web__tagesspiegel_de.py create mode 100644 services/web__taz_de.py create mode 100644 services/web__welt_de.py create mode 100644 services/web__zeit_de.py diff --git a/services/web__faz_net.py b/services/web__faz_net.py new file mode 100644 index 0000000..362313f --- /dev/null +++ b/services/web__faz_net.py @@ -0,0 +1,9 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['http://www.faz.net/aktuell/','http://www.faz.net/rss/aktuell/'] +regex = [r'https?:\/\/[^\/]*faz\.net'] +videoregex = [r'video'] +liveregex = [] +wikidata = 'Q10184' + diff --git a/services/web__focus_de.py b/services/web__focus_de.py new file mode 100644 index 0000000..dca925c --- /dev/null +++ b/services/web__focus_de.py @@ -0,0 +1,9 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www.focus.de/', 'http://rss.focus.de/fol/XML/rss_folnews.xml', 'https://rss.focus.de/fol/XML/rss_folnews_eilmeldungen.xml'] +regex = [r'https?:\/\/[^\/]*focus\.de'] +videoregex = [] +liveregex = [] +wikidata = 'Q33108673' + diff --git a/services/web__stern_de.py b/services/web__stern_de.py new file mode 100644 index 0000000..3ba3e22 --- /dev/null +++ b/services/web__stern_de.py @@ -0,0 +1,9 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www.stern.de/', 'https://www.stern.de/feed/standard/alle-nachrichten/'] +regex = [r'https?:\/\/[^\/]*stern\.de'] +videoregex = [] +liveregex = [] +wikidata = 'Q158322' + diff --git a/services/web__sueddeutsche_de.py b/services/web__sueddeutsche_de.py new file mode 100644 index 0000000..794f5f8 --- /dev/null +++ b/services/web__sueddeutsche_de.py @@ -0,0 +1,9 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['http://www.sueddeutsche.de/', 'http://rss.sueddeutsche.de/app/service/rss/alles/index.rss?output=rss'] +regex = [r'https?:\/\/[^\/]*sueddeutsche\.de'] +videoregex = [] +liveregex = [] +wikidata = 'Q158870' + diff --git a/services/web__tagesspiegel_de.py b/services/web__tagesspiegel_de.py new file mode 100644 index 0000000..e8838c0 --- /dev/null +++ b/services/web__tagesspiegel_de.py @@ -0,0 +1,9 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['http://www.tagesspiegel.de/', 'http://www.tagesspiegel.de/contentexport/feed/home'] +regex = [r'https?:\/\/[^\/]*tagesspiegel\.de'] +videoregex = [r'video\.tagesspiegel\.de'] +liveregex = [] +wikidata = 'Q10189' + diff --git a/services/web__taz_de.py b/services/web__taz_de.py new file mode 100644 index 0000000..9e06743 --- /dev/null +++ b/services/web__taz_de.py @@ -0,0 +1,9 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['http://taz.de/','http://www.taz.de/!p4608;rss/','http://blogs.taz.de/'] +regex = [r'https?:\/\/[^\/]*taz\.de'] +videoregex = [r'^https?:\/\/(?:www\.)?youtube\.com\/embed\/'] +liveregex = [] +wikidata = 'Q161423' + diff --git a/services/web__welt_de.py b/services/web__welt_de.py new file mode 100644 index 0000000..4cf5fe5 --- /dev/null +++ b/services/web__welt_de.py @@ -0,0 +1,9 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www.welt.de/'] +regex = [r'https?:\/\/[^\/]*welt\.de'] +videoregex = [] +liveregex = [] +wikidata = 'Q29872' + diff --git a/services/web__zeit_de.py b/services/web__zeit_de.py new file mode 100644 index 0000000..9bac127 --- /dev/null +++ b/services/web__zeit_de.py @@ -0,0 +1,9 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['http://www.zeit.de/index','http://newsfeed.zeit.de/all'] +regex = [r'https?:\/\/[^\/]*zeit\.de'] +videoregex = [r'\/video\/'] +liveregex = [] +wikidata = 'Q157142' + From 8b71961c08e311e782501e831b725e10c7989f53 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Constantin=20Mu=CC=88ller?= Date: Wed, 17 Jan 2018 01:00:27 +0100 Subject: [PATCH 5/8] added heise_de and golem_de from issue #6 --- services/web__golem_de.py | 9 +++++++++ services/web__heise_de.py | 9 +++++++++ 2 files changed, 18 insertions(+) create mode 100644 services/web__golem_de.py create mode 100644 services/web__heise_de.py diff --git a/services/web__golem_de.py b/services/web__golem_de.py new file mode 100644 index 0000000..a4d18e4 --- /dev/null +++ b/services/web__golem_de.py @@ -0,0 +1,9 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www.golem.de/','https://rss.golem.de/rss.php?feed=RSS0.91'] +regex = [r'https?:\/\/[^\/]*golem\.de'] +videoregex = [r'\/audio-video\/'] +liveregex = [] +wikidata = 'Q1536243' + diff --git a/services/web__heise_de.py b/services/web__heise_de.py new file mode 100644 index 0000000..8a6e4ad --- /dev/null +++ b/services/web__heise_de.py @@ -0,0 +1,9 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www.heise.de/','https://www.heise.de/newsticker/heise-atom.xml'] +regex = [r'https?:\/\/[^\/]*heise\.de'] +videoregex = [r'\/video\/'] +liveregex = [] +wikidata = 'Q1601295' + From 7838d96e2df4c669f74f3ea7880a15dd1f66c2e6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Constantin=20Mu=CC=88ller?= Date: Wed, 17 Jan 2018 19:28:01 +0100 Subject: [PATCH 6/8] added german local public news stations and there substations --- services/web__br_de.py | 24 ++++++++++++++++++++++++ services/web__hr_de.py | 23 +++++++++++++++++++++++ services/web__mdr_de.py | 9 +++++++++ services/web__ndr_de.py | 21 +++++++++++++++++++++ services/web__radiobremen_de.py | 14 ++++++++++++++ services/web__rbb-online_de.py | 17 +++++++++++++++++ services/web__sr_de.py | 18 ++++++++++++++++++ services/web__swr_de.py | 21 +++++++++++++++++++++ services/web__wdr_de.py | 20 ++++++++++++++++++++ 9 files changed, 167 insertions(+) create mode 100644 services/web__br_de.py create mode 100644 services/web__hr_de.py create mode 100644 services/web__mdr_de.py create mode 100644 services/web__ndr_de.py create mode 100644 services/web__radiobremen_de.py create mode 100644 services/web__rbb-online_de.py create mode 100644 services/web__sr_de.py create mode 100644 services/web__swr_de.py create mode 100644 services/web__wdr_de.py diff --git a/services/web__br_de.py b/services/web__br_de.py new file mode 100644 index 0000000..2275549 --- /dev/null +++ b/services/web__br_de.py @@ -0,0 +1,24 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['http://www.br.de/nachrichten/index.html', + 'https://www.br.de/nachrichten/aktuell-100~rss.xml', + 'https://www.br.de/radio/bayern2/bayern-zwei108~rss.xml', + 'https://www.br.de/nachrichten/aktuell-100~rss.xml', + 'https://www.br.de/radio/br-klassik/br-klassik112~rss.xml', + 'https://www.br.de/fernsehen/bayerisches-fernsehen/bayerisches-fernsehen108~rss.xml', + 'https://www.br.de/on3/puls-homepage100~rss.xml', + 'https://www.br.de/fernsehen/ard-alpha/ard-alpha106~rss.xml', + 'https://www.br.de/mediathek/video/suche/tag-suche-mediathek-100~rss.jsp?q=mostViewed&t=social', + 'http://www.br.de/nachrichten/niederbayern/regionalnachrichten-niederbayern-100~rss.xml', + 'http://www.br.de/nachrichten/oberbayern/regionalnachrichten-oberbayern-100~rss.xml', + 'http://www.br.de/nachrichten/oberpfalz/regionalnachrichten-oberpfalz-100~rss.xml', + 'https://www.br.de/nachrichten/schwaben/regionalnachrichten-schwaben-100~rss.xml', + 'https://www.br.de/franken/franken100~rss.xml', + 'https://www.br.de/unternehmen/index112~rss.xml', + 'https://www.br.de/presse/index152~rss.xml'] +regex = [r'https?:\/\/[^\/]*br\.de', r'https?:\/\/[^\/]*br-i\.akamaihd\.net'] +videoregex = [r'\/video\/'] +liveregex = [] +wikidata = 'Q278637' + diff --git a/services/web__hr_de.py b/services/web__hr_de.py new file mode 100644 index 0000000..0db99b0 --- /dev/null +++ b/services/web__hr_de.py @@ -0,0 +1,23 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['http://www.hr.de/index.html', + 'http://www.hessenschau.de/index.html', + 'http://www.hessenschau.de/index.rss', + 'http://www.hr1.de/index.html', + 'http://www.hr1.de/index.rss', + 'http://www.hr2.de/index.html', + 'http://www.hr2.de/index.rss', + 'http://www.hr3.de/index.html', + 'http://www.hr3.de/themen/index.rss', + 'http://www.hr4.de/index.html', + 'http://www.hr-inforadio.de/index.html', + 'http://www.hr-inforadio.de/index.rss', + 'http://www.you-fm.de/index.html', + 'http://www.you-fm.de/index.rss', + 'http://www.hr-fernsehen.de/index.html'] +regex = [r'https?:\/\/[^\/]*hr\.de', r'https?:\/\/[^\/]*hessenschau\.de', r'https?:\/\/[^\/]*hr1\.de', r'https?:\/\/[^\/]*hr2\.de', r'https?:\/\/[^\/]*hr3\.de', r'https?:\/\/[^\/]*hr4\.de', r'https?:\/\/[^\/]*hr-inforadio\.de', r'https?:\/\/[^\/]*you-fm\.de', r'https?:\/\/[^\/]*hr-a\.akamaihd\.net', r'https?:\/\/[^\/]*hr-fernsehen\.de'] +videoregex = [r'\/video-'] +liveregex = [] +wikidata = 'Q23565' + diff --git a/services/web__mdr_de.py b/services/web__mdr_de.py new file mode 100644 index 0000000..a44a6e9 --- /dev/null +++ b/services/web__mdr_de.py @@ -0,0 +1,9 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www.mdr.de/'] +regex = [r'https?:\/\/[^\/]*mdr\.de', r'https?:\/\/[^\/]*jumpradio\.de', r'https?:\/\/[^\/]*mdronline-vh\.akamaihd\.net'] +videoregex = [r'\/video-'] +liveregex = [] +wikidata = 'Q158948' + diff --git a/services/web__ndr_de.py b/services/web__ndr_de.py new file mode 100644 index 0000000..9f92c80 --- /dev/null +++ b/services/web__ndr_de.py @@ -0,0 +1,21 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www.ndr.de/', + 'https://www.ndr.de/nachrichten/index.html', + 'https://www.ndr.de/ndr1niedersachsen/', + 'https://www.ndr.de/radiomv/', + 'https://www.ndr.de/wellenord/', + 'https://www.ndr.de/903/', + 'https://www.ndr.de/ndr2/', + 'https://www.ndr.de/info/', + 'http://www.n-joy.de/', + 'https://www.ndr.de/ndrkultur/', + 'https://www.ndr.de/ndrblue/', + 'https://www.ndr.de/infospezial/', + 'https://www.ndr.de/ndrplus/'] +regex = [r'https?:\/\/[^\/]*ndr\.de', r'https?:\/\/[^\/]*ndrod-vh\.akamaihd\.net', r'https?:\/\/[^\/]*n-joy\.de', r'https?:\/\/[^\/]*ndrod-vh\.akamaihd\.net'] +videoregex = [] +liveregex = [] +wikidata = 'Q201275' + diff --git a/services/web__radiobremen_de.py b/services/web__radiobremen_de.py new file mode 100644 index 0000000..5e355f6 --- /dev/null +++ b/services/web__radiobremen_de.py @@ -0,0 +1,14 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['http://www.radiobremen.de/', + 'http://www.radiobremen.de/bremeneins/index.html', + 'http://www.radiobremen.de/bremenzwei/index.html', + 'http://www.radiobremen.de/bremenvier/index.html', + 'http://www.radiobremen.de/bremennext/index.html', + 'http://www.radiobremen.de/fernsehen/index.html'] +regex = [r'https?:\/\/[^\/]*radiobremen\.de', r'https?:\/\/[^\/]*rbprogressivedl-a\.akamaihd\.net'] +videoregex = [] +liveregex = [] +wikidata = 'Q694837' + diff --git a/services/web__rbb-online_de.py b/services/web__rbb-online_de.py new file mode 100644 index 0000000..7757674 --- /dev/null +++ b/services/web__rbb-online_de.py @@ -0,0 +1,17 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www.rbb-online.de/fernsehen/', + 'https://www.rbb24.de/', + 'https://www.rbb-online.de/radio/', + 'https://www.antennebrandenburg.de/', + 'https://www.radioberlin.de/', + 'https://www.radioeins.de/', + 'https://www.inforadio.de/', + 'https://www.kulturradio.de/', + 'https://www.fritz.de/'] +regex = [r'https?:\/\/[^\/]*rbb-online\.de', r'https?:\/\/[^\/]*rbb24\.de', r'https?:\/\/[^\/]*antennebrandenburg\.de', r'https?:\/\/[^\/]*radioberlin\.de', r'https?:\/\/[^\/]*radioeins\.de', r'https?:\/\/[^\/]*inforadio\.de', r'https?:\/\/[^\/]*kulturradio\.de', r'https?:\/\/[^\/]*fritz\.de', r'https?:\/\/[^\/]*rbbmediapmdp-a\.akamaihd\.net'] +videoregex = [r'\/fernsehen\/'] +liveregex = [] +wikidata = 'Q19899' + diff --git a/services/web__sr_de.py b/services/web__sr_de.py new file mode 100644 index 0000000..0072734 --- /dev/null +++ b/services/web__sr_de.py @@ -0,0 +1,18 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www.sr.de/', + 'https://www.sr-mediathek.de/', + 'http://www.sr.de/sr/sr1/index.html', + 'http://www.sr.de/sr/sr2/index.html', + 'http://www.sr.de/sr/sr3/index.html', + 'http://www.unserding.de/unserding/index.html', + 'http://mediathek.unserding.de/index.php?seite=2', + 'http://mediathek.unserding.de/index.php?seite=3', + 'http://www.sr.de/sr/antennesaar/index.html', + 'http://www.sr.de/sr/fernsehen/index.html'] +regex = [r'https?:\/\/[^\/]*sr\.de', r'https?:\/\/[^\/]*sr-mediathek\.de', r'https?:\/\/[^\/]*unserding\.de', r'https?:\/\/[^\/]*sr_hls_od-vh\.akamaihd\.net'] +videoregex = [r'\/fernsehen\/'] +liveregex = [] +wikidata = 'Q691047' + diff --git a/services/web__swr_de.py b/services/web__swr_de.py new file mode 100644 index 0000000..527f5d0 --- /dev/null +++ b/services/web__swr_de.py @@ -0,0 +1,21 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www.swr.de/', + 'https://www.swrfernsehen.de/', + 'https://www.swr.de/swraktuell/', + 'https://www.swr.de/swr-classic/', + 'https://www.swr.de/wissen/', + 'https://www.kindernetz.de/', + 'https://www.swr.de/swr1/rp/', + 'https://www.swr.de/swr1/bw/', + 'https://www.swr.de/swr2/', + 'https://www.swr3.de/', + 'https://www.swr.de/swr4/rp/', + 'https://www.swr.de/swr4/bw', + 'https://www.dasding.de/'] +regex = [r'https?:\/\/[^\/]*swr\.de', r'https?:\/\/[^\/]*swrfernsehen\.de', r'https?:\/\/[^\/]*swr3\.de', r'https?:\/\/[^\/]*kindernetz\.de', r'https?:\/\/[^\/]*dasding\.de', r'https?:\/\/[^\/]*hlsodswr-vh\.akamaihd\.net'] +videoregex = [r'\/player\.htm'] +liveregex = [] +wikidata = 'Q700133' + diff --git a/services/web__wdr_de.py b/services/web__wdr_de.py new file mode 100644 index 0000000..d15cafc --- /dev/null +++ b/services/web__wdr_de.py @@ -0,0 +1,20 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www1.wdr.de/', + 'https://www1.wdr.de/fernsehen/startseite/index.html', + 'https://www1.wdr.de/radio/1live/uebersicht-einslive-100.html?1livestart=true', + 'https://www1.wdr.de/radio/wdr2/index.html', + 'https://www1.wdr.de/radio/wdr3/index.html', + 'https://www1.wdr.de/radio/wdr4/index.html', + 'https://www1.wdr.de/radio/wdr5/index.html', + 'https://www1.wdr.de/radio/cosmo/index.html', + 'http://www1.wdr.de/uebersicht-100.feed', + 'https://www1.wdr.de/kinder/radio/kiraka/index.html', + 'https://www1.wdr.de/radio/wdr-event/index.html', + 'https://www1.wdr.de/mediathek/video/index.html'] +regex = [r'https?:\/\/[^\/]*wdr\.de', r'https?:\/\/[^\/]*wdradaptiv-vh\.akamaihd\.net', r'https?:\/\/[^\/]*wdrmedien-a\.akamaihd\.net'] +videoregex = [r'\/video\/'] +liveregex = [] +wikidata = 'Q203453' + From ac278fa2ae86a11ab3e10e592313f337978a4982 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Constantin=20Mu=CC=88ller?= Date: Wed, 17 Jan 2018 19:52:29 +0100 Subject: [PATCH 7/8] added german local BSC Sachsen News network --- services/web__bsc_sachsen_de.py | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 services/web__bsc_sachsen_de.py diff --git a/services/web__bsc_sachsen_de.py b/services/web__bsc_sachsen_de.py new file mode 100644 index 0000000..ee84c1e --- /dev/null +++ b/services/web__bsc_sachsen_de.py @@ -0,0 +1,14 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www.radiodresden.de/nachrichten/dresden/', + 'https://www.radioleipzig.de/nachrichten/leipzig/', + 'https://www.radiochemnitz.de/nachrichten/chemnitz/', + 'https://www.radiolausitz.de/nachrichten/lausitz/', + 'https://www.radiozwickau.de/nachrichten/zwickau/', + 'https://www.radioerzgebirge.de/nachrichten/erzgebirge/'] +regex = [r'https?:\/\/[^\/]*radiodresden\.de', r'https?:\/\/[^\/]*radioleipzig\.de', r'https?:\/\/[^\/]*radiochemnitz\.de', r'https?:\/\/[^\/]*radiolausitz\.de', r'https?:\/\/[^\/]*radiozwickau\.de', r'https?:\/\/[^\/]*radioerzgebirge\.de'] +videoregex = [] +liveregex = [] +wikidata = 'Q2210561' + From 9fb172cea4fc67d9c10ce812a2666eadeb5e113a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Constantin=20Mu=CC=88ller?= Date: Thu, 18 Jan 2018 20:13:57 +0100 Subject: [PATCH 8/8] added regional news sites (saxony, germany) --- services/web__alles-lausitz_de.py | 9 +++++++ services/web__dnn_de.py | 13 +++++++++ services/web__freiepresse_de.py | 17 ++++++++++++ services/web__goerlitzer-anzeiger_de.py | 9 +++++++ services/web__lvz_de.py | 16 +++++++++++ services/web__meidresden_de.py | 9 +++++++ services/web__sz-online_de.py | 35 +++++++++++++++++++++++++ services/web__tag24_de.py | 16 +++++++++++ services/web__wochenkurier_info.py | 12 +++++++++ 9 files changed, 136 insertions(+) create mode 100644 services/web__alles-lausitz_de.py create mode 100644 services/web__dnn_de.py create mode 100644 services/web__freiepresse_de.py create mode 100644 services/web__goerlitzer-anzeiger_de.py create mode 100644 services/web__lvz_de.py create mode 100644 services/web__meidresden_de.py create mode 100644 services/web__sz-online_de.py create mode 100644 services/web__tag24_de.py create mode 100644 services/web__wochenkurier_info.py diff --git a/services/web__alles-lausitz_de.py b/services/web__alles-lausitz_de.py new file mode 100644 index 0000000..84eed79 --- /dev/null +++ b/services/web__alles-lausitz_de.py @@ -0,0 +1,9 @@ +refresh = 21600 +version = 20180116.01 + +urls = ['http://www.alles-lausitz.de/index.html'] +regex = [r'https?:\/\/[^\/]*alles-lausitz\.de'] +videoregex = [] +liveregex = [] + + diff --git a/services/web__dnn_de.py b/services/web__dnn_de.py new file mode 100644 index 0000000..f3000e2 --- /dev/null +++ b/services/web__dnn_de.py @@ -0,0 +1,13 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['http://www.dnn.de/', + 'http://www.dnn.de/rss/feed/dnn_nachrichten', + 'http://www.dnn.de/rss/feed/dnn_dresden', + 'http://www.dnn.de/rss/feed/dnn_region', + 'http://www.dnn-trauer.de/'] +regex = [r'https?:\/\/[^\/]*dnn\.de', r'https?:\/\/[^\/]*dnn-online\.de', r'https?:\/\/[^\/]*dnn-trauer\.de'] +videoregex = [] +liveregex = [] +wikidata = 'Q1258554' + diff --git a/services/web__freiepresse_de.py b/services/web__freiepresse_de.py new file mode 100644 index 0000000..279bd9c --- /dev/null +++ b/services/web__freiepresse_de.py @@ -0,0 +1,17 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www.freiepresse.de/', + 'https://gedenken.freiepresse.de/', + 'https://www.freiepresse.de/RSS/index.php?feed=https://www.freiepresse.de/RSS/rss_regional.php&nodis=0', + 'https://www.freiepresse.de/RSS/rss_regional.php', + 'https://www.freiepresse.de/RSS/rss_chemnitz.php', + 'https://www.freiepresse.de/RSS/rss_erzgebirge.php', + 'https://www.freiepresse.de/RSS/rss_mittelsachsen.php', + 'https://www.freiepresse.de/RSS/rss_vogtland.php', + 'https://www.freiepresse.de/RSS/rss_zwickau.php'] +regex = [r'https?:\/\/[^\/]*freiepresse\.de'] +videoregex = [] +liveregex = [] +wikidata = 'Q896460' + diff --git a/services/web__goerlitzer-anzeiger_de.py b/services/web__goerlitzer-anzeiger_de.py new file mode 100644 index 0000000..a1832a6 --- /dev/null +++ b/services/web__goerlitzer-anzeiger_de.py @@ -0,0 +1,9 @@ +refresh = 21600 +version = 20180116.01 + +urls = ['http://www.goerlitzer-anzeiger.de/'] +regex = [r'https?:\/\/[^\/]*goerlitzer-anzeiger\.de'] +videoregex = [r'video'] +liveregex = [] + + diff --git a/services/web__lvz_de.py b/services/web__lvz_de.py new file mode 100644 index 0000000..cded521 --- /dev/null +++ b/services/web__lvz_de.py @@ -0,0 +1,16 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['http://www.lvz.de/', + 'http://www.lvz.de/rss/feed/lvz_nachrichten', + 'http://www.lvz.de/rss/feed/lvz_leipzig', + 'http://www.lvz.de/Leipzig/Lokales', + 'http://www.lvz.de/rss/feed/lvz_region', + 'http://www.lvz.de/rss/feed/lvz_mitteldeutschland', + 'http://www.lvz.de/Region', + 'http://www.lvz-trauer.de/'] +regex = [r'https?:\/\/[^\/]*lvz\.de', r'https?:\/\/[^\/]*lvz-online\.de', r'https?:\/\/[^\/]*lvz-trauer\.de'] +videoregex = [] +liveregex = [] +wikidata = 'Q283347' + diff --git a/services/web__meidresden_de.py b/services/web__meidresden_de.py new file mode 100644 index 0000000..2b50490 --- /dev/null +++ b/services/web__meidresden_de.py @@ -0,0 +1,9 @@ +refresh = 21600 +version = 20180116.01 + +urls = ['https://www.meidresden.de/'] +regex = [r'https?:\/\/[^\/]*meidresden\.de'] +videoregex = [] +liveregex = [] + + diff --git a/services/web__sz-online_de.py b/services/web__sz-online_de.py new file mode 100644 index 0000000..da729de --- /dev/null +++ b/services/web__sz-online_de.py @@ -0,0 +1,35 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['http://www.sz-online.de/', + 'http://www.sz-online.de/nachrichten/', + 'http://www.sz-trauer.de/nachrufe-und-traueranzeigen?_fstatus=browse;type=all_memorial', + 'http://www.sz-trauer.de/traueranzeigen?_fstatus=browse;type=death', + 'http://www.sz-online.de/Sachsen.rss', + 'http://www.sz-online.de/Bautzen.rss', + 'http://www.sz-online.de/Bischofswerda.rss', + 'http://www.sz-online.de/Doebeln.rss', + 'http://www.sz-online.de/Dresdner-Land.rss', + 'http://www.sz-online.de/Freital.rss', + 'http://www.sz-online.de/Goerlitz.rss', + 'http://www.sz-online.de/Grossenhain.rss', + 'http://www.sz-online.de/Hoyerswerda.rss', + 'http://www.sz-online.de/Kamenz.rss', + 'http://www.sz-online.de/Loebau.rss', + 'http://www.sz-online.de/Meissen.rss', + 'http://www.sz-online.de/Niesky.rss', + 'http://www.sz-online.de/Pirna.rss', + 'http://www.sz-online.de/Riesa.rss', + 'http://www.sz-online.de/Roedertal.rss', + 'http://www.sz-online.de/Sebnitz.rss', + 'http://www.sz-online.de/Weisswasser.rss', + 'http://www.sz-online.de/Zittau.rss', + 'http://www.sz-online.de/Dippoldiswalde.rss', + 'http://www.sz-online.de/Dresden.rss', + 'http://www.sz-online.de/Bautzen-Focus.rss', + 'http://www.sz-online.de/Politik.rss'] +regex = [r'https?:\/\/[^\/]*sz-online\.de', r'https?:\/\/[^\/]*sz-trauer\.de'] +videoregex = [] +liveregex = [] +wikidata = 'Q2378692' + diff --git a/services/web__tag24_de.py b/services/web__tag24_de.py new file mode 100644 index 0000000..9e19177 --- /dev/null +++ b/services/web__tag24_de.py @@ -0,0 +1,16 @@ +refresh = 1800 +version = 20180116.01 + +urls = ['https://www.tag24.de/dresden', + 'https://www.tag24.de/berlin', + 'https://www.tag24.de/chemnitz', + 'https://www.tag24.de/frankfurt', + 'https://www.tag24.de/leipzig', + 'https://www.tag24.de/ostwestfalen', + 'https://www.tag24.de/stuttgart', + 'https://www.tag24.de/thueringen', + 'https://www.tag24.de/'] +regex = [r'https?:\/\/[^\/]*tag24\.de'] +videoregex = [] +liveregex = [] + diff --git a/services/web__wochenkurier_info.py b/services/web__wochenkurier_info.py new file mode 100644 index 0000000..a3668aa --- /dev/null +++ b/services/web__wochenkurier_info.py @@ -0,0 +1,12 @@ +refresh = 7200 +version = 20180116.01 + +urls = ['http://www.wochenkurier.info/', + 'http://www.wochenkurier.info/sachsen/aktuelles/rss2.xml', + 'http://www.wochenkurier.info/suedbrandenburg/aktuelles/rss2.xml', + 'http://www.wochenkurier.info/service/videochannel/'] +regex = [r'https?:\/\/[^\/]*wochenkurier\.info'] +videoregex = [r'\/videochannel\/'] +liveregex = [] +wikidata = 'Q47459705' +