diff --git a/RAAspotter.py b/RAAspotter.py index fbd34c78480176a30eb45d6765818a8dff840978..1e83b18901d9390706cf7c5170f8995b60208e40 100644 --- a/RAAspotter.py +++ b/RAAspotter.py @@ -124,14 +124,15 @@ class RAAspotter: soup = BeautifulSoup(page_content, 'html.parser') sub_pages = [] for a in soup.select(element): - url = f"{host}{a['href']}" - sub_page_content = self.get_page(url).content - if not self.has_pdf(sub_page_content): - logger.info(f'{url} ne contient pas de PDF, on récupère ses sous-pages') - for sub_sub_page in self.get_sub_pages(sub_page_content, element, host): - sub_pages.append(sub_sub_page) - else: - sub_pages.append(url) + if a.get('href'): + url = f"{host}{a['href']}" + sub_page_content = self.get_page(url).content + if not self.has_pdf(sub_page_content): + logger.info(f'{url} ne contient pas de PDF, on récupère ses sous-pages') + for sub_sub_page in self.get_sub_pages(sub_page_content, element, host): + sub_pages.append(sub_sub_page) + else: + sub_pages.append(url) return sub_pages def get_raa_with_pager(self, pages_list, pager_element, host=""):