Move web scraping logic into data_request

app/data_request.py

@@ -1,6 +1,10 @@
+from re import findall
+from typing import List
+
+from bs4 import BeautifulSoup
 from requests import get
 
-from constants import URL
+from constants import FLICKR_URL, URL
 
 
 def format_url(dataset) -> str:
@@ -21,3 +25,26 @@ def request_dataset(dataset):
     response.raise_for_status()
     data = response.json()
     return data
+
+
+def request_flickr(keywords) -> str:
+    """
+    Returns the HTML of a Flickr search
+    """
+    search_url = FLICKR_URL.format(keywords)
+    result = get(search_url)
+    html = result.text
+    return html
+
+
+def scrap_flickr(keywords) -> List[str]:
+    """
+    Creates a list of image links from a Flickr search
+    """
+    html = request_flickr(keywords)
+    soup = BeautifulSoup(html, features="html.parser")
+    images = soup.find_all(
+        "div", class_="view photo-list-photo-view requiredToShowOnServer awake",
+    )
+    image_links = findall("(live.staticflickr.com/\S+.jpg)", str(images))
+    return image_links

constants.py

@@ -5,6 +5,7 @@ DATASETS = [
     "deconfinement-rues-amenagees-pour-pietons",
 ]
 URL = "https://opendata.paris.fr/api/records/1.0/search/?dataset={}&q=&rows=-1"
+FLICKR_URL = "https://www.flickr.com/search/?text={}"
 COLUMNS = {
     "deconfinement-pistes-cyclables-temporaires": [
         "fields.geo_shape.coordinates",