Search code examples
pythonjsonbeautifulsoupkeyerror

I am getting a KeyError on a JSON that I scraped


I have scraped a JSON from a website. When trying to iterate through the JSON I get a KeyError, but I'm unsure why. The loop is within the length of the JSON. Any ideas as to what is going on?

import requests
from bs4 import BeautifulSoup
import json
import pandas as pd

headers = {
    "User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:90.0) Gecko/20100101 Firefox/90.0"
}
url = "https://employment.ucsd.edu/jobs?page_size=250&page_number=1&keyword=clinical%20lab%20scientist&location_city" \
      "=Remote&location_city=San%20Diego&location_city=Encinitas&location_city=Murrieta&location_city=La%20Jolla" \
      "&location_city=Not%20Specified&location_city=Vista&sort_by=score&sort_order=DESC "
request = requests.get(url, headers=headers)
response = BeautifulSoup(request.text, "html.parser")
all_data = response.find_all("script", {"type": "application/ld+json"})
df = pd.DataFrame(columns=("Title", "Department", "Salary Range", "Appointment Percent", "URL"))

for data in all_data:
    jsn = json.loads(data.string)
    jsn_length = len(jsn['itemListElement'])
    # print(json.dumps(jsn, indent=4))
    n = 0
    while n < jsn_length:
        # print(jsn['itemListElement'][n])
        print(n)
        df['URL'] = jsn['itemListElement'][n]
        n += 1

Edit: response

Traceback (most recent call last):
  File "C:\Program Files\JetBrains\PyCharm 2022.1\plugins\python\helpers\pydev\pydevd.py", line 1491, in _exec
    pydev_imports.execfile(file, globals, locals)  # execute the script
  File "C:\Program Files\JetBrains\PyCharm 2022.1\plugins\python\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "C:/Users/Will/PycharmProjects/UCSD_JOB_SCRAPE/main.py", line 19, in <module>
    jsn_length = len(jsn['itemListElement'])
KeyError: 'itemListElement'

Solution

  • To get list of URLs into a DataFrame you can use next example:

    import json
    import requests
    import pandas as pd
    from bs4 import BeautifulSoup
    
    headers = {
        "User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:90.0) Gecko/20100101 Firefox/90.0"
    }
    
    url = (
        "https://employment.ucsd.edu/jobs?page_size=250&page_number=1&keyword=clinical%20lab%20scientist&location_city"
        "=Remote&location_city=San%20Diego&location_city=Encinitas&location_city=Murrieta&location_city=La%20Jolla"
        "&location_city=Not%20Specified&location_city=Vista&sort_by=score&sort_order=DESC "
    )
    
    request = requests.get(url, headers=headers)
    soup = BeautifulSoup(request.content, "html.parser")
    
    data = json.loads(soup.find("script", {"type": "application/ld+json"}).text)
    
    urls = []
    for e in data["itemListElement"]:
        urls.append(e["url"])
    
    df = pd.DataFrame({"URL": urls})
    print(df.head())
    

    Prints:

                                                                                        URL
    0      http://employment.ucsd.edu/clinical-lab-scientist-specialist-119559/job/20822209
    1      http://employment.ucsd.edu/clinical-lab-scientist-specialist-120139/job/21460814
    2      http://employment.ucsd.edu/clinical-lab-scientist-specialist-120483/job/21869984
    3   http://employment.ucsd.edu/sr-clinical-lab-scientist-specialist-118105/job/20528292
    4  http://employment.ucsd.edu/cls-clinical-lab-scientist-specialist-119095/job/20528293