Merge pull request #134 from thebigG/job_id

-Provider names are used as a prefix for job ids now.
PaulMcInnis · Feb 16, 2021 · 446e9e0 · 446e9e0
2 parents e509ef4 + 728849f
commit 446e9e0
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 1 deletion.
diff --git a/jobfunnel/__init__.py b/jobfunnel/__init__.py
@@ -1,3 +1,3 @@
 """JobFunnel base package init, we keep module version here.
 """
-__version__ = '3.0.1'
+__version__ = '3.0.2'
diff --git a/jobfunnel/backend/scrapers/base.py b/jobfunnel/backend/scrapers/base.py
@@ -343,6 +343,9 @@ def scrape_job(self, job_soup: BeautifulSoup, delay: float,
         if job and not invalid_job:
             try:
                 job.validate()
+                # Prefix the id with the scraper name to avoid key conflicts
+                new_key_id = job.provider + '_' + job.key_id
+                job.key_id = new_key_id
             except Exception as err:
                 # Bad job scrapes can't take down execution!
                 # NOTE: desc too short etc, usually indicates that the job

diff --git a/readme.md b/readme.md
@@ -97,6 +97,11 @@ Open the master CSV file and update the per-job `status`:
   ```
   funnel inline -h
   ```
+
+# CAPTCHA
+  JobFunnel does not solve CAPTCHA. If, while scraping, you receive a 
+  `Unable to extract jobs from initial search result page:\` error. 
+  Then open that url on your browser and solve the CAPTCHA manually.
 
 <!-- links -->
 [requirements]:requirements.txt