aboutsummaryrefslogtreecommitdiff
path: root/scrape_ecourtindia_v6/modules/scraper_orders.py
diff options
context:
space:
mode:
authorRaghuram Subramani <raghus2247@gmail.com>2025-03-27 23:05:13 +0530
committerRaghuram Subramani <raghus2247@gmail.com>2025-03-27 23:05:13 +0530
commita02c8f4c8643b4b9a531e185813c5d82b6866ec0 (patch)
treea3cdd49df8412e63ac711c148df6814efa0a05e7 /scrape_ecourtindia_v6/modules/scraper_orders.py
parent7195110a466b0ed14de1b8ee4fa8d7bb79626018 (diff)
update
Diffstat (limited to 'scrape_ecourtindia_v6/modules/scraper_orders.py')
-rw-r--r--scrape_ecourtindia_v6/modules/scraper_orders.py84
1 files changed, 79 insertions, 5 deletions
diff --git a/scrape_ecourtindia_v6/modules/scraper_orders.py b/scrape_ecourtindia_v6/modules/scraper_orders.py
index 78594e8..a9fe7be 100644
--- a/scrape_ecourtindia_v6/modules/scraper_orders.py
+++ b/scrape_ecourtindia_v6/modules/scraper_orders.py
@@ -1,17 +1,25 @@
from time import sleep
+import tempfile
+import uuid
+import os
+
+from urllib import request
+
+from bs4 import BeautifulSoup
+
+import cv2
+import pytesseract
from selenium.webdriver.common.by import By
from selenium.webdriver.support.select import Select
-from tinydb import TinyDB
-
from .scraper import Scraper
class ScraperOrders(Scraper):
- def __init__(self, config):
- Scraper.__init__(self, 'https://services.ecourts.gov.in/ecourtindia_v6/?p=courtorder/index')
+ def __init__(self, db, config):
+ Scraper.__init__(self, 'https://services.ecourts.gov.in/ecourtindia_v6/?p=courtorder/index', headless=True)
- self.db = TinyDB('db.json')
+ self.db = db
self.config = config
def goto_courtnumber(self):
@@ -27,3 +35,69 @@ class ScraperOrders(Scraper):
print(f'COURT NUMBERS: {court_numbers}')
return court_numbers
+
+ def submit_search(self):
+ captcha_incomplete = True
+ while captcha_incomplete:
+ img = self.driver.find_element(By.ID, 'captcha_image')
+ temp = tempfile.NamedTemporaryFile(suffix='.png')
+ img.screenshot(temp.name)
+
+ img = cv2.imread(temp.name)
+ text = pytesseract.image_to_string(img).strip()
+
+ element = self.driver.find_element(By.ID, 'order_no_captcha_code')
+ element.send_keys(text)
+
+ self.driver.execute_script('submitCourtNumber()')
+ sleep(3)
+
+ if self.driver.find_element(By.CLASS_NAME, 'alert-danger-cust').is_displayed():
+ self.close_modal()
+ element.clear()
+ else:
+ captcha_incomplete = False
+
+ def parse_orders_table(self):
+ try:
+ table_innerhtml = self.driver.find_element(By.ID, 'dispTable').get_attribute('innerHTML')
+ except:
+ return
+
+ rows = BeautifulSoup(str(table_innerhtml), 'html.parser').find_all('td')
+ self.rows = []
+ i = 6
+ while i < len(rows):
+ self.rows.append([ rows[i], rows[i-1].text, rows[i-2].text, rows[i-3].text ])
+ i += 5
+
+ def handle_orders(self):
+ for row in self.rows:
+ order = row[0]
+
+ script = order.find_all('a')[0].get_attribute_list('onclick')[0]
+ self.driver.execute_script(script)
+
+ sleep(0.7)
+ obj = self.driver.find_elements(By.TAG_NAME, 'object')[-1]
+ pdf_url = str(obj.get_attribute('data'))
+
+ while True:
+ filename = f"pdf/{uuid.uuid4().hex}.pdf"
+ if not os.path.exists(filename):
+ break
+
+ cookies = "; ".join([f"{c['name']}={c['value']}" for c in self.driver.get_cookies()])
+ r = request.Request(pdf_url)
+ r.add_header("Cookie", cookies)
+
+ try:
+ with request.urlopen(r) as response, open(filename, "wb") as file:
+ file.write(response.read())
+ except:
+ print(f'UNABLE TO FETCH PDF: {pdf_url}')
+
+ record = { 'case_info': row[3], 'petitioner_respondent': row[2], 'date': row[1], 'filename': filename }
+ self.db.insert(record)
+
+ self.driver.find_element(By.ID, 'modalOders').find_element(By.CLASS_NAME, 'btn-close').click()