def tvn24():
t24Headlines=dict()
tvn24="https://www.tvn24.pl/"
page= urllib.request.urlopen(tvn24)
soup = bs(page, features="html.parser")
# print(soup.prettify())
#main news:
mainHeadlines=soup.find_all("h1")
for headline in mainHeadlines:
tags=headline.find_all("a")
for tag in tags:
# print("TVN24: " + str(tag.get_text()))
key = randomStringDigits(8)
value = tag.get_text()
t24Headlines[key] = value
#side news:
sideHeadlines=soup.find_all("h2")
for headline in sideHeadlines:
if headline.has_attr('class'):
aTag=headline.find("a")
if aTag is not None:
if headline['class'][0]=="decorate-heading" and len(str(aTag.string))>30:
# print("TVN24: " + str(aTag.string).strip())
key = randomStringDigits(8)
value = str(aTag.get_text()).strip()
t24Headlines[key] = value
return t24Headlines
def tvpinfo():
tHeadlines = dict()
tvp = "https://www.tvp.info/"
page = urllib.request.urlopen(tvp)
soup = bs(page, features="html.parser")
# main news:
mainHeadlines = soup.find_all("h1", class_="title")
for headline in mainHeadlines:
# print("TVP Info: " + str(headline.string).strip())
key = randomStringDigits(8)
value = str(headline.string).strip()
tHeadlines[key] = value
# major news:
majorNewsHeadlines = soup.find_all("h2", class_="news__title")
for headline in majorNewsHeadlines:
# print("TVP Info: " + str(headline.string).strip())
key = randomStringDigits(8)
value = str(headline.string).strip()
tHeadlines[key] = value
# minor news:
minorNewsHeadlines = soup.find_all("h3", class_="news__title")
for headline in minorNewsHeadlines:
# print("TVP Info: " + str(headline.string).strip())
key = randomStringDigits(8)
value = str(headline.string).strip()
tHeadlines[key] = value
# info:
infoHeadlines = soup.find_all("h3", class_="information__text")
for headline in infoHeadlines:
# print("TVP Info: " + str(headline.string).strip())
key = randomStringDigits(8)
value = str(headline.string).strip()
tHeadlines[key] = value
# business:
businessHeadlines = soup.find_all("h3", class_="business__subtitle")
for headline in businessHeadlines:
# print("TVP Info: " + str(headline.string).strip())
key = randomStringDigits(8)
value = str(headline.string).strip()
tHeadlines[key] = value
return tHeadlines
def wpolityce():
wpolHeadlines=dict()
wpolityce="https://wpolityce.pl"
page= urllib.request.urlopen(wpolityce)
soup = bs(page, features="html.parser")
headlines=soup.find_all("span", class_="long-title")
for headline in headlines:
# print("WPolityce: " + str(headline.string))
key=randomStringDigits(8)
val=str(headline.string)
wpolHeadlines[key]=val
return wpolHeadlines
def onet():
oHeadlines = dict()
onet = "https://wiadomosci.onet.pl/"
page = urllib.request.urlopen(onet)
soup = bs(page, features="html.parser")
headlines = soup.find_all("h3")
for headline in headlines:
# print("Onet: " + str(headline.string))
key = randomStringDigits(8)
value = str(headline.string)
oHeadlines[key] = value
return oHeadlines
def rmfswiat():
rsHeadlines=dict()
rmfWorld="https://www.rmf24.pl/fakty/swiat"
page= urllib.request.urlopen(rmfWorld)
soup = bs(page, features="html.parser")
headlines=soup.find_all("div", class_="boxBody")
for headline in headlines:
imgs=headline.find_all("img")
for img in imgs:
key = randomStringDigits(8)
value = str(img['alt']).strip().replace(u'\u200b','')
rsHeadlines[key] = value
return rsHeadlines
def wp():
wpHeadlines = dict()
wp = "https://www.wp.pl/"
page = urllib.request.urlopen(wp)
soup = bs(page, features="html.parser")
# print(soup.prettify())
# news type 1:
headlines = soup.find_all("div", class_="sc-1bp8799-1 gqsna")
for headline in headlines:
# print("WP: " + str(headline.get_text()))
key = randomStringDigits(8)
val = str(headline.get_text())
wpHeadlines[key] = val
# news type 2:
headlines2 = soup.find_all("div", class_="lclzf3-0 egPcYF")
for headline in headlines2:
# print("WP: " + str(headline.get_text()))
key = randomStringDigits(8)
val = str(headline.get_text()).strip()
wpHeadlines[key] = val.strip()
return wpHeadlines
def polityka():
pHeadlines = dict()
polityka = "https://www.polityka.pl/TygodnikPolityka"
page = urllib.request.urlopen(polityka)
soup = bs(page, features="html.parser")
# side headlines
sideHeadlines = soup.find_all("h3")
for headline in sideHeadlines:
if headline.string is not None:
# print("Polityka: " + str(headline.string).strip())
key = randomStringDigits(8)
value = str(headline.string).strip()
pHeadlines[key] = value
return pHeadlines
def rmfpolska():
rpHeadlines=dict()
rmfPoland="https://www.rmf24.pl/fakty/polska"
page= urllib.request.urlopen(rmfPoland)
soup = bs(page, features="html.parser")
# print(soup.prettify())
headlines=soup.find_all("div", class_="boxBody")
for headline in headlines:
imgs=headline.find_all("img")
for img in imgs:
# print("RMF Polska: " + str(img['alt']))
key = randomStringDigits(8)
value = str(img['alt']).strip()
rpHeadlines[key] = value
return rpHeadlines
def newsweek():
nHeadlines = dict()
newsweek = "https://www.newsweek.pl/"
page = urllib.request.urlopen(newsweek)
soup = bs(page, features="html.parser")
# print(soup.prettify())
headlines = soup.find_all("h2", class_="artTitle")
for headline in headlines:
# print(headline)
if headline.string is not None:
key = randomStringDigits(8)
value = str(headline.string)
nHeadlines[key] = value
return nHeadlines
def fronda():
fHeadlines = dict()
frondaurl = "http://www.fronda.pl/c/wiadomosci,1.html"
hdr = {'User-Agent': 'Mozilla/5.0'}
req = Request(frondaurl, headers=hdr)
page = urlopen(req)
soup = bs(page, features="html.parser")
# print(soup.prettify())
headlines = soup.find_all("h4")
for headline in headlines:
# print("Fronda: " + str(headline.string))
key = randomStringDigits(8)
value = str(headline.string)
fHeadlines[key] = value
return fHeadlines
def nczas():
ncHeadlines = dict()
nczas = "https://nczas.com/"
hdr = {'User-Agent': 'Mozilla/5.0'}
req = Request(nczas, headers=hdr)
page = urlopen(req)
soup = bs(page, features="html.parser")
headlines = soup.find_all("h3", class_="entry-title td-module-title")
for headline in headlines:
titles = headline.find_all("a")
for title in titles:
# print("NCzas: " + str(title['title']))
key = randomStringDigits(8)
value = str(title.string)
ncHeadlines[key] = value
return ncHeadlines
def gazeta():
gHeadlines = dict()
gazeta = "http://wiadomosci.gazeta.pl/wiadomosci/0,0.html"
page = urllib.request.urlopen(gazeta)
soup = bs(page, features="html.parser")
# print(soup.prettify())
headlines = soup.find_all("li", class_="entry")
for headline in headlines:
titles = headline.find_all("a")
for title in titles:
if title.string is not None:
# print("Gazeta: " + str(title.string))
key = randomStringDigits(8)
value = str(title.string)
gHeadlines[key] = value
return gHeadlines
def wprost():
wprHeadlines = dict()
wprost = "https://www.wprost.pl/wiadomosci"
page = urllib.request.urlopen(wprost)
soup = bs(page, features="html.parser")
# print(soup.prettify())
headlines = soup.find_all("span")
for headline in headlines:
if headline.string is not None:
if len(str(headline.string)) > 30:
key = randomStringDigits(8)
val = str(headline.string).replace(u'\xa0', ' ')
wprHeadlines[key] = val
return wprHeadlines
# print(wprost())
def interia():
iHeadlines = dict()
interia = "https://fakty.interia.pl/"
page = urllib.request.urlopen(interia)
soup = bs(page, features="html.parser")
headlines = soup.find_all("li")
for headline in headlines:
magazines = headline.find_all("div", class_="tile-magazine")
for magazine in magazines:
headers = magazine.find_all("div", class_="tile-magazine-header")
for header in headers:
titles = header.find_all("h2", class_="tile-magazine-title")
for title in titles:
# print("Interia: " + str(title.find("a").string))
key = randomStringDigits(8)
value = str(title.find("a").string)
val = value.replace(u'\u200b', '')
iHeadlines[key] = val
return iHeadlines