removed commas in fields

job_scraper_exact_match.py

@@ -1,12 +1,26 @@
-import csv
-import datetime
 import os
+import datetime
 from jobspy.google import Google
 from jobspy.linkedin import LinkedIn
 from jobspy.indeed import Indeed
 from jobspy.ziprecruiter import ZipRecruiter
 from jobspy.model import ScraperInput
 
+def clean_text(text: str) -> str:
+    """
+    Cleans text for CSV output by removing or replacing characters
+    that could break CSV formatting.
+    """
+    if not text:
+        return ""
+    # Remove commas, newlines, carriage returns and double quotes.
+    cleaned = text.replace(",", " ") \
+                  .replace("\n", " ") \
+                  .replace("\r", " ") \
+                  .replace('"', "'")
+    # Collapse multiple spaces into one.
+    return " ".join(cleaned.split())
+
 # Define job sources
 sources = {
     "google": Google,
@@ -17,7 +31,7 @@ sources = {
 
 # Define search preferences
 search_terms = ["Automation Engineer", "CRM Manager", "Implementation Specialist", "Automation", "CRM"]
-results_wanted = 200  # Fetch more jobs
+results_wanted = 100  # Fetch more jobs
 max_days_old = 2      # Fetch jobs posted in last 48 hours
 target_state = "NY"   # Only keep jobs from New York
 
@@ -50,22 +64,21 @@ def scrape_jobs(search_terms, results_wanted, max_days_old, target_state):
                 # Debug: Show all jobs being fetched
                 print(f"📍 Fetched Job: {job.title} - {location_city}, {location_state}, {location_country}")
 
-                # 🔥 Exclude jobs that don’t explicitly match the search terms
+                # Exclude jobs that don’t explicitly match the search terms
                 if not any(term.lower() in job.title.lower() for term in search_terms):
                     print(f"🚫 Excluding: {job.title} (Doesn't match {search_terms})")
-                    continue  # Skip this job
+                    continue
 
-                # Ensure the job is recent
+                # Ensure the job is recent and in NY (or remote)
                 if job.date_posted and (today - job.date_posted).days <= max_days_old:
-                    # Only accept jobs if they're in NY or Remote
                     if location_state == target_state or job.is_remote:
                         print(f"✅ MATCH: {job.title} - {location_city}, {location_state} (Posted {job.date_posted})")
                         all_jobs.append({
                             "Job ID": job.id,
-                            "Job Title (Primary)": job.title,
+                            "Job Title (Primary)": clean_text(job.title),
-                            "Company Name": job.company_name if job.company_name else "Unknown",
+                            "Company Name": clean_text(job.company_name) if job.company_name else "Unknown",
-                            "Industry": job.company_industry if job.company_industry else "Not Provided",
+                            "Industry": clean_text(job.company_industry) if job.company_industry else "Not Provided",
-                            "Experience Level": job.job_level if job.job_level else "Not Provided",
+                            "Experience Level": clean_text(job.job_level) if job.job_level else "Not Provided",
                             "Job Type": job.job_type[0].name if job.job_type else "Not Provided",
                             "Is Remote": job.is_remote,
                             "Currency": job.compensation.currency if job.compensation else "",
@@ -76,7 +89,7 @@ def scrape_jobs(search_terms, results_wanted, max_days_old, target_state):
                             "Location State": location_state,
                             "Location Country": location_country,
                             "Job URL": job.job_url,
-                            "Job Description": job.description.replace(",", "") if job.description else "No description available",
+                            "Job Description": clean_text(job.description) if job.description else "No description available",
                             "Job Source": source_name
                         })
                     else:
@@ -87,9 +100,8 @@ def scrape_jobs(search_terms, results_wanted, max_days_old, target_state):
     print(f"\n✅ {len(all_jobs)} jobs retrieved in NY")
     return all_jobs
 
-
 def save_jobs_to_csv(jobs, filename="jobspy_output.csv"):
-    """Save job data to a CSV file."""
+    """Save job data to a CSV file with a custom delimiter."""
     if not jobs:
         print("⚠️ No jobs found matching criteria.")
         return
@@ -106,14 +118,20 @@ def save_jobs_to_csv(jobs, filename="jobspy_output.csv"):
         "Job Source"
     ]
 
-    with open(filename, mode="w", newline="", encoding="utf-8") as file:
+    # Define your custom delimiter
-        writer = csv.DictWriter(file, fieldnames=fieldnames)
+    delimiter = "|~|"
-        writer.writeheader()
+
-        writer.writerows(jobs)
+    with open(filename, mode="w", encoding="utf-8") as file:
+        # Write header
+        file.write(delimiter.join(fieldnames) + "\n")
+        # Write each job record
+        for job in jobs:
+            # Convert all field values to string
+            row = [str(job.get(field, "")) for field in fieldnames]
+            file.write(delimiter.join(row) + "\n")
 
     print(f"✅ Jobs saved to {filename} ({len(jobs)} entries)")
 
-
 # Run the scraper with multiple job searches
 job_data = scrape_jobs(
     search_terms=search_terms,

jobspy/ziprecruiter/__init__.py

@@ -9,10 +9,11 @@ from datetime import datetime
 
 from bs4 import BeautifulSoup
 
+import cloudscraper  # NEW: Use cloudscraper to bypass Cloudflare
+
 from jobspy.ziprecruiter.constant import headers, get_cookie_data
 from jobspy.util import (
     extract_emails_from_text,
-    create_session,
     markdown_converter,
     remove_attributes,
     create_logger,
@@ -41,15 +42,20 @@ class ZipRecruiter(Scraper):
         self, proxies: list[str] | str | None = None, ca_cert: str | None = None
     ):
         """
-        Initializes ZipRecruiterScraper with the ZipRecruiter job search url
+        Initializes ZipRecruiterScraper with the ZipRecruiter job search url.
+        This version uses cloudscraper to bypass Cloudflare's anti-bot challenge.
         """
         super().__init__(Site.ZIP_RECRUITER, proxies=proxies)
 
-        self.scraper_input = None
+        # Use cloudscraper instead of the standard session to handle Cloudflare.
-        self.session = create_session(proxies=proxies, ca_cert=ca_cert)
+        self.session = cloudscraper.create_scraper()
+        if proxies:
+            self.session.proxies = proxies
+
         self.session.headers.update(headers)
         self._get_cookies()
 
+        self.scraper_input = None
         self.delay = 5
         self.jobs_per_page = 20
         self.seen_urls = set()
@@ -86,10 +92,10 @@ class ZipRecruiter(Scraper):
         self, scraper_input: ScraperInput, continue_token: str | None = None
     ) -> tuple[list[JobPost], str | None]:
         """
-        Scrapes a page of ZipRecruiter for jobs with scraper_input criteria
+        Scrapes a page of ZipRecruiter for jobs with scraper_input criteria.
         :param scraper_input:
         :param continue_token:
-        :return: jobs found on page
+        :return: jobs found on page.
         """
         jobs_list = []
         params = add_params(scraper_input)
@@ -123,7 +129,7 @@ class ZipRecruiter(Scraper):
 
     def _process_job(self, job: dict) -> JobPost | None:
         """
-        Processes an individual job dict from the response
+        Processes an individual job dict from the response.
         """
         title = job.get("name")
         job_url = f"{self.base_url}/jobs//j?lvk={job['listing_key']}"
@@ -184,16 +190,16 @@ class ZipRecruiter(Scraper):
             job_descr_div = soup.find("div", class_="job_description")
             company_descr_section = soup.find("section", class_="company_description")
             job_description_clean = (
-                remove_attributes(job_descr_div).prettify(formatter="html")
+                remove_attributes(job_descr_div).get_text(separator="\n", strip=True)
                 if job_descr_div
                 else ""
             )
             company_description_clean = (
-                remove_attributes(company_descr_section).prettify(formatter="html")
+                remove_attributes(company_descr_section).get_text(separator="\n", strip=True)
                 if company_descr_section
                 else ""
             )
-            description_full = job_description_clean + company_description_clean
+            description_full = job_description_clean + "\n" + company_description_clean
 
             try:
                 script_tag = soup.find("script", type="application/json")