Fix GlassDoor Country Vietnam(#122)

README.md

@@ -104,15 +104,6 @@ JobPost
 └── is_remote (bool)
 ```
 
-### Exceptions
-
-The following exceptions may be raised when using JobSpy:
-
-* `LinkedInException`
-* `IndeedException`
-* `ZipRecruiterException`
-* `GlassdoorException`
-
 ## Supported Countries for Job Searching
 
 ### **LinkedIn**
@@ -147,7 +138,7 @@ You can specify the following countries when searching on Indeed (use the exact
 | South Korea          | Spain*       | Sweden     | Switzerland*   |
 | Taiwan               | Thailand     | Turkey     | Ukraine        |
 | United Arab Emirates | UK*          | USA*       | Uruguay        |
-| Venezuela            | Vietnam      |            |                |
+| Venezuela            | Vietnam*     |            |                |
 
 
 Glassdoor can only fetch 900 jobs from the endpoint we're using on a given search.

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.46"
+version = "1.1.47"
 description = "Job scraper for LinkedIn, Indeed, Glassdoor & ZipRecruiter"
 authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
 homepage = "https://github.com/Bunsly/JobSpy"
@@ -17,8 +17,8 @@ beautifulsoup4 = "^4.12.2"
 pandas = "^2.1.0"
 NUMPY = "1.24.2"
 pydantic = "^2.3.0"
-html2text = "^2020.1.16"
 tls-client = "^1.0.1"
+markdownify = "^0.11.6"
 
 
 [tool.poetry.group.dev.dependencies]

src/jobspy/jobs/__init__.py

@@ -122,7 +122,7 @@ class Country(Enum):
     USA = ("usa,us,united states", "www", "com")
     URUGUAY = ("uruguay", "uy")
     VENEZUELA = ("venezuela", "ve")
-    VIETNAM = ("vietnam", "vn")
+    VIETNAM = ("vietnam", "vn", "com")
 
     # internal for ziprecruiter
     US_CANADA = ("usa/ca", "www")

src/jobspy/scrapers/utils.py

@@ -1,15 +1,14 @@
-import re
 import logging
-import numpy as np
+import re
 
-import html2text
-import tls_client
+import numpy as np
 import requests
+import tls_client
+from markdownify import markdownify as md
 from requests.adapters import HTTPAdapter, Retry
 
 from ..jobs import JobType
 
-text_maker = html2text.HTML2Text()
 logger = logging.getLogger("JobSpy")
 logger.propagate = False
 if not logger.handlers:
@@ -36,13 +35,9 @@ def count_urgent_words(description: str) -> int:
 
 def markdown_converter(description_html: str):
     if description_html is None:
-        return ""
-    text_maker.ignore_links = False
-    try:
-        markdown = text_maker.handle(description_html)
-        return markdown.strip()
-    except AssertionError as e:
-        return ""
+        return None
+    markdown = md(description_html)
+    return markdown.strip()
 
 
 def extract_emails_from_text(text: str) -> list[str] | None: