def get_current_openings_page(self, job_page): fetcher = PageFetcher() page_source = fetcher.fetch_page(job_page) soup = BeautifulSoup(page_source, 'html.parser') current_openings_link = soup.find("a", string=re.compile("openings", re.I), href=True) if current_openings_link: return resolve_one_relative_page(self.url, current_openings_link['href']) else: link = soup.find("a", string=re.compile("open positions", re.I), href=True) if link: return resolve_one_relative_page(self.url, link['href']) else: return job_page
def find_posting_links(self, soup): links = soup.find_all( "a", href=re.compile( "https?://\\w+\\.applytojob\\.com/apply/\\w+/\\w+")) return [ resolve_one_relative_page(self.get_ats_url(soup), link['href']) for link in links ]
def find_alternative_pages(self, soup): links = [] links.extend( soup.find_all("a", string=re.compile("more", re.I), href=True)) links.extend( soup.find_all("a", string=re.compile("about us", re.I), href=True)) return [ resolve_one_relative_page(self.url, link['href']) for link in links ]
def find_posting_links(self, soup): links = soup.find_all("a", href=re.compile("/\\w+/jobs/[0-9]+")) return [resolve_one_relative_page(self.get_ats_url(soup), link['href']) for link in links]
def find_posting_links(self, soup): links = soup.find_all("a", href=re.compile("https?://\\w+\\.applytojob\\.com/apply/\\w+/\\w+")) return [resolve_one_relative_page(self.get_ats_url(soup), link['href']) for link in links]
def find_alternative_pages(self, soup): links = [] links.extend(soup.find_all("a", string=re.compile("more", re.I), href=True)) links.extend(soup.find_all("a", string=re.compile("about us", re.I), href=True)) return [resolve_one_relative_page(self.url, link['href']) for link in links]
def find_posting_links(self, soup): links = soup.find_all("a", href=re.compile("/\\w+/jobs/[0-9]+")) return [ resolve_one_relative_page(self.get_ats_url(soup), link['href']) for link in links ]