chore: version number

JobSpy_Demo.ipynb

@@ -9,7 +9,7 @@
    "source": [
     "from jobspy import scrape_jobs\n",
     "import pandas as pd\n",
-    "from IPython.display import display, HTML\n"
+    "from IPython.display import display, HTML"
    ]
   },
   {
@@ -34,18 +34,16 @@
    "source": [
     "# example 1 (no hyperlinks, USA)\n",
     "jobs = scrape_jobs(\n",
-    "    site_name=[\"linkedin\", \"zip_recruiter\"],\n",
+    "    site_name=[\"linkedin\"],\n",
     "    location='san francisco',\n",
     "    search_term=\"engineer\",\n",
     "    results_wanted=5,\n",
     "\n",
     "    # use if you want to use a proxy\n",
-    "    # proxy=\"socks5://jobspy:5a4vpWtj8EeJ2hoYzk@ca.smartproxy.com:20001\",\n",
+    "    # proxy=\"socks5://jobspy:5a4vpWtj4EeJ2hoYzk@us.smartproxy.com:10001\",\n",
-    "    # proxy=\"http://jobspy:5a4vpWtj8EeJ2hoYzk@ca.smartproxy.com:20001\",\n",
+    "    proxy=\"http://jobspy:5a4vpWtj4EeJ2hoYzk@us.smartproxy.com:10001\",\n",
-    "    # proxy=\"https://jobspy:5a4vpWtj8EeJ2hoYzk@ca.smartproxy.com:20001\",\n",
+    "    #proxy=\"https://jobspy:5a4vpWtj4EeJ2hoYzk@us.smartproxy.com:10001\",\n",
-    "\n",
     ")\n",
-    "\n",
     "display(jobs)"
    ]
   },
@@ -97,9 +95,6 @@
     "    hyperlinks=True,\n",
     "    results_wanted=5,\n",
     "    easy_apply=True\n",
-    "\n",
-    "\n",
-    "\n",
     ")"
    ]
   },
@@ -125,11 +120,10 @@
    "outputs": [],
    "source": [
     "# example 4 - international indeed (no zip_recruiter)\n",
-    "result = scrape_jobs(\n",
+    "jobs = scrape_jobs(\n",
     "    site_name=[\"indeed\"],\n",
-    "    location='berlin',\n",
     "    search_term=\"engineer\",\n",
-    "    country_indeed = \"Germany\",\n",
+    "    country_indeed = \"China\",\n",
     "    hyperlinks=True\n",
     ")"
    ]
@@ -165,7 +159,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.11"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,

README.md

@@ -1,21 +1,26 @@
 <img src="https://github.com/cullenwatson/JobSpy/assets/78247585/ae185b7e-e444-4712-8bb9-fa97f53e896b" width="400">
 
 **JobSpy** is a simple, yet comprehensive, job scraping library.
+
+**Not technical?** Try out the web scraping tool on our site at [usejobspy.com](https://usejobspy.com).
+
+*Looking to build a data-focused software product?* **[Book a call](https://calendly.com/zachary-products/15min)** *to work with us.*  
+\
+Check out another project we wrote: ***[HomeHarvest](https://github.com/ZacharyHampton/HomeHarvest)** – a Python package for real estate scraping*
 ## Features
 
 
 - Scrapes job postings from **LinkedIn**, **Indeed** & **ZipRecruiter** simultaneously
 - Aggregates the job postings in a Pandas DataFrame
+- Proxy support (HTTP/S, SOCKS)
   
-[Video Guide for JobSpy](https://www.youtube.com/watch?v=-yS3mgI5H-4)
+[Video Guide for JobSpy](https://www.youtube.com/watch?v=RuP1HrAZnxs&pp=ygUgam9icyBzY3JhcGVyIGJvdCBsaW5rZWRpbiBpbmRlZWQ%3D) - Updated for release v1.1.3
-
-
 
 ![jobspy](https://github.com/cullenwatson/JobSpy/assets/78247585/ec7ef355-05f6-4fd3-8161-a817e31c5c57)
   
 ### Installation
 ```
-pip install python-jobspy
+pip install --upgrade python-jobspy
 ```
   
   _Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_ 
@@ -34,27 +39,26 @@ jobs: pd.DataFrame = scrape_jobs(
     
     country_indeed='USA' # only needed for indeed
     
-    # use if you want to use a proxy
+    # use if you want to use a proxy (3 types)
     # proxy="socks5://jobspy:5a4vpWtj8EeJ2hoYzk@ca.smartproxy.com:20001",
     # proxy="http://jobspy:5a4vpWtj8EeJ2hoYzk@ca.smartproxy.com:20001",
     # proxy="https://jobspy:5a4vpWtj8EeJ2hoYzk@ca.smartproxy.com:20001",
 )
 
+# formatting for pandas
 pd.set_option('display.max_columns', None)
 pd.set_option('display.max_rows', None)
 pd.set_option('display.width', None)
 pd.set_option('display.max_colwidth', 50)  # set to 0 to see full job url / desc
 
-#1 output
+#1 display in Jupyter Notebook (1. pip install jupyter 2. jupyter notebook)
-print(jobs)
+display(jobs)
-print(errors)
 
-#2 display in Jupyter Notebook
+#2 output to console
-#display(jobs)
+#print(jobs)
-#display(errors)
 
 #3 output to .csv
-#result.jobs.to_csv('result.jobs.csv', index=False)
+#jobs.to_csv('jobs.csv', index=False)
 ```
 
 ### Output
@@ -76,10 +80,11 @@ Optional
 ├── location (int)
 ├── distance (int): in miles
 ├── job_type (enum): fulltime, parttime, internship, contract
+├── proxy (str): in format 'http://user:pass@host:port' or [https, socks]
 ├── is_remote (bool)
 ├── results_wanted (int): number of job results to retrieve for each site specified in 'site_type'
 ├── easy_apply (bool): filters for jobs that are hosted on LinkedIn
-├── country_indeed (enum): filters the country on Indeed
+├── country_indeed (enum): filters the country on Indeed (see below for correct spelling)
 ```
 
  
@@ -103,20 +108,26 @@ JobPost
 └── date_posted (date)
 ```
 
+### Exceptions
+The following exceptions may be raised when using JobSpy:
+* `LinkedInException`
+* `IndeedException`
+* `ZipRecruiterException`
+
 ## Supported Countries for Job Searching
 
 
 ### **LinkedIn**
 
-LinkedIn searches globally & uses only the `location` parameter
+LinkedIn searches globally & uses only the `location` parameter.
 
 ### **ZipRecruiter**
 
-ZipRecruiter searches for jobs in US/Canada & uses only the `location` parameter
+ZipRecruiter searches for jobs in **US/Canada** & uses only the `location` parameter.
 
 
 ### **Indeed**
-For Indeed, the `country_indeed` parameter is required. Additionally, use the `location` parameter and include the city or state if necessary.
+Indeed supports most countries, but the `country_indeed` parameter is required. Additionally, use the `location` parameter to narrow down the location, e.g. city & state if necessary.
 
 You can specify the following countries when searching on Indeed (use the exact name): 
 
@@ -145,18 +156,22 @@ You can specify the following countries when searching on Indeed (use the exact
 ---
 
 **Q: Encountering issues with your queries?**  
-**A:** Try reducing the number of `results_wanted` and/or broadening the filters. If problems persist, [submit an issue](#).
+**A:** Try reducing the number of `results_wanted` and/or broadening the filters. If problems persist, [submit an issue](https://github.com/cullenwatson/JobSpy/issues).
 
 ---
 
 **Q: Received a response code 429?**  
-**A:** This indicates that you have been blocked by the job board site for sending too many requests. Currently, **ZipRecruiter** is particularly aggressive with blocking. We recommend:
+**A:** This indicates that you have been blocked by the job board site for sending too many requests. Currently, **LinkedIn** is particularly aggressive with blocking. We recommend:
 
 - Waiting a few seconds between requests.
-- Trying a VPN to change your IP address.
+- Trying a VPN or proxy to change your IP address.
-
-**Note:** Proxy support is in development and coming soon!
 
 ---
 
+**Q: Experiencing a "Segmentation fault: 11" on macOS Catalina?**  
+**A:** This is due to `tls_client` dependency not supporting your architecture. Solutions and workarounds include:
+- Upgrade to a newer version of MacOS
+- Reach out to the maintainers of [tls_client](https://github.com/bogdanfinn/tls-client) for fixes
+
+
   

pyproject.toml

@@ -1,8 +1,9 @@
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.3"
+version = "1.1.7"
 description = "Job scraper for LinkedIn, Indeed & ZipRecruiter"
 authors = ["Zachary Hampton <zachary@zacharysproducts.com>", "Cullen Watson <cullen@cullen.ai>"]
+homepage = "https://github.com/cullenwatson/JobSpy"
 readme = "README.md"
 
 packages = [

src/jobspy/__init__.py

@@ -32,7 +32,7 @@ def scrape_jobs(
     location: str = "",
     distance: int = None,
     is_remote: bool = False,
-    job_type: JobType = None,
+    job_type: str = None,
     easy_apply: bool = False,  # linkedin
     results_wanted: int = 15,
     country_indeed: str = "usa",
@@ -44,6 +44,14 @@ def scrape_jobs(
     :return: results_wanted: pandas dataframe containing job data
     """
 
+    def get_enum_from_value(value_str):
+        for job_type in JobType:
+            if value_str in job_type.value:
+                return job_type
+        raise Exception(f"Invalid job type: {value_str}")
+    job_type = get_enum_from_value(job_type) if job_type else None
+
+
     if type(site_name) == str:
         site_type = [_map_str_to_site(site_name)]
     else:  #: if type(site_name) == list