This commit is contained in:
jon ander 2024-12-02 16:53:37 +01:00
parent 819bab2e5c
commit fad7ec7aa8
4 changed files with 4 additions and 4 deletions

View File

@ -2,7 +2,7 @@
<module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$" />
<orderEntry type="jdk" jdkName="Python 3.11" jdkType="Python SDK" />
<orderEntry type="inheritedJdk" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
</module>

View File

@ -3,5 +3,5 @@
<component name="Black">
<option name="sdkName" value="Python 3.13" />
</component>
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11" project-jdk-type="Python SDK" />
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.13" project-jdk-type="Python SDK" />
</project>

View File

@ -1,6 +1,6 @@
from ejercicios.paralelismo02.ej01.ej01 import MiScraping
hilo = MiScraping("http://localhost/mi_web")
hilo = MiScraping("http://localhost:8000/portada.html")
hilo.start()
hilo.join()
links = hilo.get_links()

View File

@ -11,7 +11,7 @@ class MiScraping(threading.Thread):
def run(self):
response = requests.get(self.url)
soup = BeautifulSoup(response.text,"html.parser")
self.links = [a['href'] for a in soup.find_all('a', href=True) if re.match(r'http[s]?://', a['href'])]
self.links = [a['href'] for a in soup.find_all('a', href=True)]
def get_links(self):
return self.links