Python - requests - into-action.us (Stackoverflow)

# date: 2025.09.24

# [python - Trying to scrape <a href="/media/"> from a webpage and nothing is working - Stack Overflow](https://stackoverflow.com/questions/79773927/trying-to-scrape-a-href-media-from-a-webpage-and-nothing-is-working)

import requests

session = requests.Session()

# load main page to get cookies
url = "https://library.into-action.us/collection/creative-jam-health-is-life"
response = session.get(url)

# load data
url = "https://library.into-action.us/api/v1/collections/creative-jam-health-is-life/content/"

page = 1
index = 1
while True:
    print(f"--- {page} ---")

    response = session.get(url)

    data = response.json()

    for item in data["results"]:
        # display information
        print(f'{index:4} | {item["id"]:6} | {item["static_image"]}')

        # download image if exists
        image_url = item["static_image"]
        if image_url:
            # get filename without parameters and without full path
            filename = image_url.rsplit("?")[0].rsplit("/")[-1]
            # download file
            response = session.get(image_url)
            # write in file with ID at the beginning of filename
            with open(f'{item["id"]:06}_{filename}', "wb") as f:
                f.write(response.content)

        index += 1

    # if there is no link to next page then exit loop
    if ("next" not in data) or (not data["next"]):
        break

    # get link to next page - to use it in next loop.
    url = data["next"]
    page += 1

"""
Output: (it also downloads images)

--- 1 ---
   1 |  29821 | https://into-action-green-static-files.s3.amazonaws.com/content/2025/06/02/RWJF_CJ_AnnickMartin.jpg
   2 |  29355 | https://media1.giphy.com/media/v1.Y2lkPTc5ODAyNjliaGg5dnpmMXlya2E2cndwd3JvZjU5NHF0bmt3ODV6YWd5amxpenh6cSZlcD12MV9naWZzX2dpZklkJmN0PWc/OTkwczXwJrxq1aVfFV/giphy_s.gif
   3 |  29884 | https://media0.giphy.com/media/v1.Y2lkPTc5ODAyNjliMDRjaHRxNjJiMGhhbTM5MWpyMnk3MWpiMnBqZGxqODV2NW9hdXA1bCZlcD12MV9naWZzX2dpZklkJmN0PWc/VIJeYkKhOC0ifOCfSa/giphy_s.gif
   4 |  29840 | https://media3.giphy.com/media/v1.Y2lkPTc5ODAyNjliZGJmN3phNDk2dHNlbDNmcHRpbmhxdjU1ZjA5amx3ZWk1NWlzdzlhbiZlcD12MV9naWZzX2dpZklkJmN0PWc/niFwnBm5mg5azbfV5c/giphy_s.gif
   5 |  29817 | https://into-action-green-static-files.s3.amazonaws.com/content/2025/06/02/RWJF_CJ_AlexRosales-GenevaPierre-LincolnHarrison_1.png
   6 |  29850 | https://into-action-green-static-files.s3.amazonaws.com/content/2025/06/02/RWJF_CJ_ProjectsPetite.png
   7 |  29353 | https://media3.giphy.com/media/v1.Y2lkPTc5ODAyNjliajM2cmpkajkxYWp2czh6dWtzZ29ybnFra2lybncyaXUxOWQ5cGF5NCZlcD12MV9naWZzX2dpZklkJmN0PWc/DKa0XWo3PfSyuFnZSF/giphy_s.gif
   8 |  29847 | https://into-action-green-static-files.s3.amazonaws.com/content/2025/06/02/RWJF_CJ_Melonsharks.png
   9 |  29860 | https://into-action-green-static-files.s3.amazonaws.com/content/2025/06/02/RWJF_CJ_Yaicecream.png
  10 |  29830 | https://media4.giphy.com/media/v1.Y2lkPTc5ODAyNjliYXB0cGUwdXFxdTI0MjRqcW1yZnJhNWg5MmYxZnMwNjRjMjc5M3hsMiZlcD12MV9naWZzX2dpZklkJmN0PWc/2BECd3EF7VpMmlHiuE/giphy_s.gif
  11 |  29846 | https://into-action-green-static-files.s3.amazonaws.com/content/2025/06/02/RWJF_CJ_MeghanAuer.png
"""