mirrors/pferd
1
0
Fork 0
mirror of https://github.com/Garmelon/PFERD.git synced 2023-12-21 10:23:01 +01:00
Code Issues Packages Projects Releases Wiki Activity

Adjust to new crawl / download names

Browse Source
This commit is contained in:
I-Al-Istannen 2021-05-22 23:18:05 +02:00
parent e724ff7c93
commit 953a1bba93
1 changed files with 23 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
PFERD/crawlers/ilias/kit_ilias_web_crawler.py
View File

@ -116,7 +116,7 @@ class KitIliasWebCrawler(HttpCrawler):
self._link_file_redirect_delay = section.link_file_redirect_delay()
self._link_file_use_plaintext = section.link_file_use_plaintext()
async def crawl(self) -> None:
async def _run(self) -> None:
if isinstance(self._target, int):
log.explain_topic(f"Inferred crawl target: Course with id {self._target}")
await self._crawl_course(self._target)
@ -127,11 +127,6 @@ class KitIliasWebCrawler(HttpCrawler):
log.explain_topic(f"Inferred crawl target: URL {escape(self._target)}")
await self._crawl_url(self._target)
if self.error_free:
await self.cleanup()
else:
log.explain_topic("Skipping file cleanup as errors occurred earlier")
async def _crawl_course(self, course_id: int) -> None:
# Start crawling at the given course
root_url = url_set_query_param(
@ -144,10 +139,14 @@ class KitIliasWebCrawler(HttpCrawler):
await self._crawl_url(self._base_url)
async def _crawl_url(self, url: str, expected_id: Optional[int] = None) -> None:
cl = await self.crawl(PurePath("."))
if not cl:
return
tasks = []
# TODO: Retry this when the crawl and download bar are reworked
async with self.crawl_bar(PurePath("Root element")):
async with cl:
soup = await self._get_page(url)
if expected_id is not None:
@ -165,14 +164,12 @@ class KitIliasWebCrawler(HttpCrawler):
await asyncio.gather(*tasks)
async def _handle_ilias_page(self, url: str, parent: IliasPageElement, path: PurePath) -> None:
# We might not want to crawl this directory-ish page.
# This is not in #handle_element, as the download methods check it themselves and therefore
# would perform this check twice - messing with the explain output
if not self.should_crawl(path):
cl = await self.crawl(path)
if not cl:
return
tasks = []
async with self.crawl_bar(path):
async with cl:
soup = await self._get_page(url)
page = IliasPage(soup, url, parent)
@ -189,7 +186,9 @@ class KitIliasWebCrawler(HttpCrawler):
if element.type == IliasElementType.FILE:
await self._download_file(element, element_path)
elif element.type == IliasElementType.FORUM:
log.explain_topic(f"Skipping forum at {escape(str(element_path))}")
log.explain_topic(f"Decision: Crawl {escape(str(element_path))}")
log.explain("Is a forum")
log.explain("Answer: No")
elif element.type == IliasElementType.LINK:
await self._download_link(element, element_path)
elif element.type == IliasElementType.VIDEO:
@ -208,13 +207,12 @@ class KitIliasWebCrawler(HttpCrawler):
if not dl:
return
async with self.download_bar(element_path):
async with dl as (bar, sink):
export_url = element.url.replace("cmd=calldirectlink", "cmd=exportHTML")
async with self.session.get(export_url) as response:
html_page: BeautifulSoup = soupify(await response.read())
real_url: str = html_page.select_one("a").get("href").strip()
async with dl as sink:
content = link_template_plain if self._link_file_use_plaintext else link_template_rich
content = content.replace("{{link}}", real_url)
content = content.replace("{{name}}", element.name)
@ -229,11 +227,10 @@ class KitIliasWebCrawler(HttpCrawler):
if not dl:
return
async with self.download_bar(element_path) as bar:
async with dl as (bar, sink):
page = IliasPage(await self._get_page(element.url), element.url, element)
real_element = page.get_child_elements()[0]
async with dl as sink:
await self._stream_from_url(real_element.url, sink, bar)
async def _download_file(self, element: IliasPageElement, element_path: PurePath) -> None:
@ -241,7 +238,7 @@ class KitIliasWebCrawler(HttpCrawler):
if not dl:
return
async with self.download_bar(element_path) as bar, dl as sink:
async with dl as (bar, sink):
await self._stream_from_url(element.url, sink, bar)
async def _stream_from_url(self, url: str, sink: FileSink, bar: ProgressBar) -> None: