Python: Python 3.11.2 Python Editor: PyCharm 2022.3.3 (Community Edition) - Build PC-223.8836.43 OS: Windows 11 Pro, 22H2, 22621.1413 Browser: Chrome 111.0.5563.65 (Official Build) (64-bit)
I have a URL (e.g., https://dockets.justia.com/docket/puerto-rico/prdce/3:2023cv01127/175963
) from which I'm scraping nine items. I'm looking to have the script create a csv file and write my scraped output (nine items) to columns in the csv file. Is there a really simple way of doing this?
from bs4 import BeautifulSoup
import requests
import csv
html_text = requests.get("https://dockets.justia.com/docket/puerto-rico/prdce/3:2023cv01127/175963").text
soup = BeautifulSoup(html_text, "lxml")
cases = soup.find_all("div", class_ = "wrapper jcard has-padding-30 blocks has-no-bottom-padding")
for case in cases:
case_title = case.find("div", class_ = "title-wrapper").text.replace(" "," ")
case_plaintiff = case.find("td", {"data-th": "Plaintiff"}).text.replace(" "," ")
case_defendant = case.find("td", {"data-th": "Defendant"}).text.replace(" "," ")
case_number = case.find("td", {"data-th": "Case Number"}).text.replace(" "," ")
case_filed = case.find("td", {"data-th": "Filed"}).text.replace(" "," ")
court = case.find("td", {"data-th": "Court"}).text.replace(" "," ")
case_nature_of_suit = case.find("td", {"data-th": "Nature of Suit"}).text.replace(" "," ")
case_cause_of_action = case.find("td", {"data-th": "Cause of Action"}).text.replace(" "," ")
jury_demanded = case.find("td", {"data-th": "Jury Demanded By"}).text.replace(" "," ")
print(f"{case_title.strip()}")
print(f"{case_plaintiff.strip()}")
print(f"{case_defendant.strip()}")
print(f"{case_number.strip()}")
print(f"{case_filed.strip()}")
print(f"{court.strip()}")
print(f"{case_nature_of_suit.strip()}")
print(f"{case_cause_of_action.strip()}")
print(f"{jury_demanded.strip()}")
source https://stackoverflow.com/questions/75803901/is-there-a-really-simple-method-for-printing-scraped-output-to-a-csv-file
Comments
Post a Comment