Last active
November 12, 2020 17:52
-
-
Save LvanWissen/1aa74dee61e85923826b6372a24f9367 to your computer and use it in GitHub Desktop.
Download van metadata (csv + json) van alle affiches uit het Afficheproject van het Geheugen van Nederland (Delpher)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import json | |
import requests | |
import pandas as pd | |
from bs4 import BeautifulSoup | |
URL = "https://geheugen.delpher.nl/nl/geheugen/results?query=Eye+AND+afficheproject&maxperpage=1000&coll=ngvn&page=" | |
def main(destination, pages, URL=URL): | |
data = getData(pages=pages, URL=URL) | |
with open(f'{destination}.json', 'w') as outfile: | |
json.dump(data, outfile, indent=4) | |
df = pd.DataFrame(data) | |
df.T.to_csv(f'{destination}.csv', sep=';') | |
def getData(pages, URL): | |
data = dict() | |
for i in range(1, pages+1): | |
fetchUrl = URL + str(i) | |
r = requests.get(fetchUrl) | |
html = r.text | |
data = parseHTML(html, data=data) | |
return data | |
def parseHTML(html, data): | |
soup = BeautifulSoup(html) | |
articles = soup.find_all('article') | |
for a in articles: | |
uri = a.attrs['data-identifier'] | |
metadata = json.loads(a.attrs['data-metadata']) | |
data[uri] = metadata | |
return data | |
if __name__ == "__main__": | |
main(destination="eye_afficheproject", pages=52, URL=URL) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment