Riksdag search
Incomplete scraper pieces
PAGE = "https://www.riksdagen.se/sv/webb-tv/video/beslut/teckensprakstolkat-beslut-ja-till-nya-mojligheter_hdc5uulkgixzejmvaqlott/"
import requests
from bs4 import BeautifulSoup
import json
def get_embedded_json(url):
response = requests.get(url)
soup = BeautifulSoup(response.content, 'html.parser')
script_tag = soup.find('script', {"type": 'application/json', "id": "__NEXT_DATA__"})
if script_tag:
data = json.loads(script_tag.text)
return data
return None
data = get_embedded_json(PAGE)
def get_documentid(data):
return data.get("props", None).get("pageProps", None).get("contentApiData", None).get("documentId", None)
get_documentid(data)
SEARCH = "https://www.riksdagen.se/sv/sok/?avd=webbtv&lang=sgn"
STS_SEARCH = "https://www.riksdagen.se/sv/sok/?avd=webbtv&lang=sgn&p="
def read_web_search_results(tpl, num_pages=1):
response = requests.get(tpl + str(num_pages))
soup = BeautifulSoup(response.content, 'html.parser')
results = []
next_link = soup.find('a', {"aria-label": "Nästa sida"})
has_next = next_link is not None
sres = soup.find_all('div', class_='flex')
for res in sres:
link_tag = res.find('a', {"href": True, "aria-label": True})
if link_tag:
if link_tag['href'].startswith('https://'):
if not link_tag['href'] in results:
results.append(link_tag['href'])
return results, has_next
read_web_search_results(STS_SEARCH, 1)
https://www.riksdagen.se/sv/teckensprak/kontakta-riksdagen/ https://www.riksdagen.se/globalassets/12.-teckensprak/kontakta-riksdagen_720p.mp4
https://www.riksdagen.se/sv/teckensprak/sa-fungerar-eu/vad-gor-eu/ https://redigera.riksdagen.se/globalassets/12.-teckensprak/vad-gor-eu.mp4
https://www.riksdagen.se/sv/teckensprak/sa-fungerar-eu/vad-kostar-eu/ https://redigera.riksdagen.se/globalassets/12.-teckensprak/vad-kostar-eu-2024.mp4
https://www.riksdagen.se/sv/teckensprak/sa-fungerar-eu/nar-eu-beslutar/ https://www.riksdagen.se/globalassets/12.-teckensprak/nar-eu-beslutar.mp4
https://www.riksdagen.se/sv/teckensprak/sa-fungerar-riksdagen/ https://redigera.riksdagen.se/globalassets/12.-teckensprak/sa-fungerar-riksdagen_720p.mp4
https://www.riksdagen.se/sv/teckensprak/sa-fungerar-riksdagen/demokrati/