fix:correct LinkedIn logger naming (#291)

* fix:correct LinkedIn logger naming

* add:linkedin description plain format

Author: lixianphys

jobspy/__init__.py

@@ -107,6 +107,7 @@ def scrape_site(site: Site) -> Tuple[str, JobResponse]:
         scraped_data: JobResponse = scraper.scrape(scraper_input)
         cap_name = site.value.capitalize()
         site_name = "ZipRecruiter" if cap_name == "Zip_recruiter" else cap_name
+        site_name = "LinkedIn" if cap_name == "Linkedin" else cap_name
         create_logger(site_name).info(f"finished scraping")
         return site.value, scraped_data
 

jobspy/linkedin/__init__.py

@@ -35,6 +35,7 @@
     extract_emails_from_text,
     currency_parser,
     markdown_converter,
+    plain_converter,
     create_session,
     remove_attributes,
     create_logger,
@@ -267,7 +268,8 @@ def _get_job_details(self, job_id: str) -> dict:
             description = div_content.prettify(formatter="html")
             if self.scraper_input.description_format == DescriptionFormat.MARKDOWN:
                 description = markdown_converter(description)
-
+            elif self.scraper_input.description_format == DescriptionFormat.PLAIN:
+                description = plain_converter(description)
         h3_tag = soup.find(
             "h3", text=lambda text: text and "Job function" in text.strip()
         )

jobspy/model.py

@@ -234,7 +234,7 @@ class Compensation(BaseModel):
 class DescriptionFormat(Enum):
     MARKDOWN = "markdown"
     HTML = "html"
-
+    PLAIN = "plain"
 
 class JobPost(BaseModel):
     id: str | None = None

jobspy/util.py

@@ -157,6 +157,15 @@ def markdown_converter(description_html: str):
     markdown = md(description_html)
     return markdown.strip()
 
+def plain_converter(decription_html:str):
+    from bs4 import BeautifulSoup
+    if decription_html is None:
+        return None
+    soup = BeautifulSoup(decription_html, "html.parser")
+    text = soup.get_text(separator=" ")
+    text = re.sub(r'\s+',' ',text)
+    return text.strip()
+
 
 def extract_emails_from_text(text: str) -> list[str] | None:
     if not text: