Changeset View
Changeset View
Standalone View
Standalone View
swh/lister/cgit/lister.py
# Copyright (C) 2019-2021 The Software Heritage developers | # Copyright (C) 2019-2021 The Software Heritage developers | ||||
# License: GNU General Public License version 3, or any later version | # License: GNU General Public License version 3, or any later version | ||||
# See top-level LICENSE file for more information | # See top-level LICENSE file for more information | ||||
from datetime import datetime, timezone | from datetime import datetime, timezone | ||||
import logging | import logging | ||||
import re | import re | ||||
from typing import Any, Dict, Iterator, List, Optional | from typing import Any, Dict, Iterator, List, Optional | ||||
from urllib.parse import urljoin, urlparse | from urllib.parse import urljoin, urlparse | ||||
from bs4 import BeautifulSoup | from bs4 import BeautifulSoup | ||||
import requests | import requests | ||||
from requests.exceptions import HTTPError | from requests.exceptions import HTTPError | ||||
from tenacity.before_sleep import before_sleep_log | |||||
from swh.lister import USER_AGENT | from swh.lister import USER_AGENT | ||||
from swh.lister.pattern import CredentialsType, StatelessLister | from swh.lister.pattern import CredentialsType, StatelessLister | ||||
from swh.lister.utils import throttling_retry | |||||
from swh.scheduler.interface import SchedulerInterface | from swh.scheduler.interface import SchedulerInterface | ||||
from swh.scheduler.model import ListedOrigin | from swh.scheduler.model import ListedOrigin | ||||
logger = logging.getLogger(__name__) | logger = logging.getLogger(__name__) | ||||
Repositories = List[Dict[str, Any]] | Repositories = List[Dict[str, Any]] | ||||
▲ Show 20 Lines • Show All 44 Lines • ▼ Show 20 Lines | ): | ||||
) | ) | ||||
self.session = requests.Session() | self.session = requests.Session() | ||||
self.session.headers.update( | self.session.headers.update( | ||||
{"Accept": "application/html", "User-Agent": USER_AGENT} | {"Accept": "application/html", "User-Agent": USER_AGENT} | ||||
) | ) | ||||
self.base_git_url = base_git_url | self.base_git_url = base_git_url | ||||
@throttling_retry(before_sleep=before_sleep_log(logger, logging.DEBUG)) | |||||
def _get_and_parse(self, url: str) -> BeautifulSoup: | def _get_and_parse(self, url: str) -> BeautifulSoup: | ||||
"""Get the given url and parse the retrieved HTML using BeautifulSoup""" | """Get the given url and parse the retrieved HTML using BeautifulSoup""" | ||||
response = self.session.get(url) | response = self.session.get(url) | ||||
response.raise_for_status() | response.raise_for_status() | ||||
return BeautifulSoup(response.text, features="html.parser") | return BeautifulSoup(response.text, features="html.parser") | ||||
def get_pages(self) -> Iterator[Repositories]: | def get_pages(self) -> Iterator[Repositories]: | ||||
"""Generate git 'project' URLs found on the current CGit server | """Generate git 'project' URLs found on the current CGit server | ||||
▲ Show 20 Lines • Show All 125 Lines • Show Last 20 Lines |