def main():
site = Site()
site.name = "serienjunkies"
site.alias = "serienjunkies"
site.short = "sj"
site.base_url = "https://serienjunkies.de"
site.channel_id = -1001422493025
raw_data = feedparser.parse("https://www.serienjunkies.de/rss/news.xml")
for x in raw_data["entries"]:
link_match = re.findall("(.*\.html)", x['link'])
link = link_match[0] if link_match else x['link']
if site.check_article_exists(link):
continue
img, tags = get_img_and_tags(x["link"])
site.add_article(text=x["summary"],
title=x["title"],
link=link,
tags=tags,
img=img)
site.post()
def main():
site = Site()
site.name = "sueddeutsche"
site.alias = "Süddeutsche"
site.short = "sz"
site.base_url = "https://sueddeutsche.de/"
site.channel_id = -1001356683060
site.instant_id = -1001431408008
site.join_instant = "https://t.me/joinchat/AAAAAFVRjYiqwgQUBJvWqQ"
raw_data = feedparser.parse("https://rss.sueddeutsche.de/rss/Topthemen")
for x in raw_data["entries"]:
img, tags = get_img_and_tags(x["link"])
site.add_article(text=x["summary"],
title=x["title"],
link=x["link"],
img=img,
tags=tags)
site.post()
def main():
site = Site()
site.name = "tagesthemen_de"
site.alias = "tagesschau.de"
site.short = "tages"
site.base_url = "https://www.tagesschau.de/xml/rss2"
site.channel_id = -1001151817211
site.instant_id = -1001450868426
site.join_instant = "http://t.me/joinchat/AAAAAFZ6fsojLN6G1q2rmA"
raw_data = feedparser.parse("https://www.tagesschau.de/xml/atom/")
for x in raw_data["entries"]:
if x["link"] in [
"https://novi.funk.net",
"http://blog.ard-hauptstadtstudio.de",
]:
continue
if site.check_article_exists(x["link"]):
continue
img, tags = get_img_and_tags(x["link"])
site.add_article(text=x["summary"],
title=x["title"],
link=x["link"],
tags=tags,
img=img)
site.post()
def main():
site = Site()
site.name = "brohltal"
site.alias = "BrohltalInfo24"
site.base_url = "http://www.brohltal-info24.de/"
site.channel_id = -1001131410143
site.short = "brohl"
for article in get_data(site.base_url):
text, tags = create_hashtag(article[2])
site.add_article(
img=site.base_url + article[0],
title=article[1],
text=text,
tags=tags,
date=article[4],
link=site.base_url + article[3],
)
site.post(variant=3)
def main():
site = Site()
site.name = "focus_de"
site.alias = "Focus Online"
site.short = "focus"
site.base_url = "https://www.focus.de/"
site.channel_id = -1001358620859
site.instant_id = -1001479434546
site.join_instant = "https://t.me/joinchat/AAAAAFguYTI39BV7VxK9qQ"
for x in feedparser.parse(
"https://rss.focus.de/fol/XML/rss_folnews_eilmeldungen.xml"
)["entries"]:
if site.check_article_exists(x["link"]):
continue
link = x["link"]
text = x["summary"]
text = re.split("\n", text, re.MULTILINE)
text = text[-1].split("<br />")[0]
img = get_img(link)
tags = [y["term"] for y in x["tags"]]
site.add_article(title=x["title"],
text=text,
link=link,
img=img,
tags=tags)
site.post()
def main():
site = Site()
site.name = "zeit_de"
site.alias = "Zeit Online"
site.short = "zeit"
site.base_url = "https://zeit-online.de/"
site.channel_id = -1001497423999
site.instant_id = -1001355451098
site.join_instant = "http://t.me/joinchat/AAAAAFDKitrF93gyfjCUeg"
raw_data = feedparser.parse("https://newsfeed.zeit.de/index")
for x in raw_data["entries"]:
if site.check_article_exists(x["link"]):
continue
img, tags = get_img_and_tags(x["link"])
site.add_article(text=x["summary"],
title=x["title"],
link=x["link"],
img=img,
tags=tags)
site.post()
def main():
site = Site()
site.name = "welt_de"
site.alias = "Welt.de"
site.short = "welt"
site.base_url = "https://welt.de/"
site.channel_id = -1001247567899
site.instant_id = -1001184127734
site.join_instant = "http://t.me/joinchat/AAAAAEaUWvabMwWbupISFw"
raw_data = feedparser.parse("https://www.welt.de/feeds/latest.rss")
for x in raw_data["entries"]:
if site.check_article_exists(x["link"]):
continue
tags = [y["term"] for y in x["tags"]]
img = (
x["links"][1]["href"]
if len(x["links"]) > 1 and x["links"][1]["type"] == "image/jpeg"
else ""
)
text = x["summary"] if "summary" in x else ""
site.add_article(
text=text, title=x["title"], link=x["link"], tags=tags, img=img
)
site.post()
def main():
site = Site()
site.name = "spiegel_online_de"
site.alias = "spiegel-online"
site.short = "spiegel"
site.base_url = "https://spiegel-online.de/"
site.channel_id = -1001442405890
site.instant_id = -1001182811341
site.join_instant = "http://t.me/joinchat/AAAAAEaARM11yh3ZtMJGXQ"
raw_data = feedparser.parse("http://www.spiegel.de/schlagzeilen/index.rss")
for x in raw_data["entries"]:
if site.check_article_exists(x["link"]):
continue
img, tags = get_img_and_tags(x["link"])
text = x["summary"] if 'summary' in x else ''
site.add_article(text=text,
title=x["title"],
link=x["link"],
tags=tags,
img=img)
site.post()
def main():
site = Site()
site.name = "pro_linux_de"
site.alias = "Pro-Linux.de"
site.short = "proli"
site.base_url = "https://www.pro-linux.de/"
site.channel_id = -1001232676629
site.instant_id = -1001499098018
site.join_instant = "https://t.me/joinchat/AAAAAFlaa6IhIGAqmFuZFQ"
raw_data = feedparser.parse(
"https://www.pro-linux.de/NB3/rss/2/4/atom_aktuell.xml")
for x in raw_data["entries"]:
if site.check_article_exists(x["link"]):
continue
img, tags = get_img_and_tags(x["link"])
site.add_article(text=x["summary"],
title=x["title"],
link=x["link"],
tags=tags,
img=img)
site.post()
def main():
for s in HEISE_SITES:
site = Site()
site.name = s['channel_link']
site.alias = s['name']
site.short = s['short']
site.channel_id = s['channel_id']
site.instant_id = s['instant_id']
site.join_instant = s['instant_link']
raw_data = feedparser.parse(s['rss'])
for x in raw_data["entries"]:
if site.check_article_exists(x["link"]):
continue
img, tags = get_img_and_tags(x["link"])
text = x["summary"] if "summary" in x else ""
site.add_article(title=x["title"],
link=x["link"],
text=text,
tags=tags,
img=img)
site.post()
def main():
site = Site()
site.name = "tageszeitung"
site.alias = "taz"
site.short = "taz"
site.base_url = "https://taz.de/"
site.channel_id = -1001152190997
raw_data = feedparser.parse("https://www.taz.de/!p4608;rss/")
for x in raw_data["entries"]:
if site.check_article_exists(x["link"]):
continue
img, tags = get_img_and_tags(x["link"])
text = x['summary'].replace("mehr...", "") if 'summary' in x else ""
site.add_article(
text=text, title=x["title"], link=x["link"], img=img, tags=tags
)
site.post()
def main():
site = Site()
site.name = "tarnkappe"
site.short = "tk"
site.alias = "Tarnkappe.info"
site.base_url = "https://tarnkappe.info/"
site.channel_id = -1001096556431
site.instant_id = -1001201795584
site.instant_hash = "ea1f50995623f3"
site.join_instant = "http://t.me/joinchat/AAAAAEeh8gAMwazWu2hoTA"
raw_data = feedparser.parse(site.base_url + "feed/")
for x in raw_data["entries"]:
if site.check_article_exists(x["link"]):
continue
sourcecode = requests.get(x["link"]).text
img = re.findall('<meta property="og:image" content="([^"]*)"',
sourcecode)[0]
tags = [y["term"] for y in x["tags"]]
site.add_article(link=x["link"],
title=x["title"],
text=x["summary"],
img=img,
tags=tags)
site.post()
def main():
for s in BILD_SITES:
site = Site()
site.name = s['channel_link']
site.alias = s['name']
site.short = s['short']
site.channel_id = s['channel_id']
site.instant_id = s['instant_id']
site.join_instant = s['instant_link']
for x in feedparser.parse(s['rss'])["entries"]:
if site.check_article_exists(x["link"]):
continue
text = ""
if "summary" in x:
text = x["summary"]
text = re.split("\n", text, re.MULTILINE)
text = text[-1].split("<br />")[0]
img = (
x["media_thumbnail"][0]["url"].replace(",w=120,", ",w=1200,")
if "media_thumbnail" in x
else None
)
tags = [y["term"] for y in x["tags"]]
site.add_article(
title=x["title"], text=text, link=x["link"], img=img, tags=tags
)
site.post()
def main():
site = Site()
site.name = "golem_de"
site.alias = "Golem.de"
site.short = "golem"
site.base_url = "https://golem.de/"
site.channel_id = -1001138540100
site.instant_id = -1001304871255
site.join_instant = "http://t.me/joinchat/AAAAAE3GwVcigPpRU96awA"
for x in feedparser.parse("https://rss.golem.de/rss.php?feed=RSS2.0")["entries"]:
if site.check_article_exists(x["link"]):
continue
text = x["summary"].split("(<a")[0]
article_code = requests.get(x["link"]).text
img = re.findall(
'"twitter:image" property="og:image" content="([^"]*)"', article_code
)[0]
tags = re.findall('a href="[^"]*">([^<]*)<', html.unescape(x["summary"]))
site.add_article(
text=text, title=x["title"], img=img, tags=tags, link=x["link"]
)
site.post()
def main():
site = Site()
site.name = "rundschau"
site.alias = "Frankfurter Rundschau"
site.short = "fr"
site.base_url = "https://fr.de/"
site.channel_id = -1001389663056
raw_data = feedparser.parse("https://www.fr.de/rssfeed.rdf")
for x in raw_data["entries"]:
if site.check_article_exists(x["link"]):
continue
img, tags = get_img_and_tags(x["link"])
text = x["summary"] if 'summary' in x else ''
site.add_article(text=text,
title=x["title"],
link=x["link"],
tags=tags,
img=img)
site.post()
def main():
site = Site()
site.name = "olbrueck"
site.alias = "Olbrück Rundschau"
site.base_url = "https://archiv.wittich.de/epapers/pdf/3"
site.short = "olbrück"
site.channel_id = -1001199332289
for i in range(10):
result = get_newspaper(site, week=(i - 5) * -1)
if result:
title, jpg, url = tuple(result)
site.add_article(title=title, img=jpg, link=url)
site.post(4)