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

Improve log messages when parsing ILIAS HTML

Browse Source 
Previously some logs were split around an "await", which isn't a great
idea.
This commit is contained in:
I-Al-Istannen 2021-05-27 17:59:22 +02:00
parent 474aa7e1cc
commit 1ca6740e05
2 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
PFERD/crawl/ilias/kit_ilias_html.py
View File

@ -142,7 +142,7 @@ class IliasPage:
url: str = self._abs_url_from_link(content_link) url: str = self._abs_url_from_link(content_link)
query_params = {"limit": "800", "cmd": "asyncGetTableGUI", "cmdMode": "asynch"} query_params = {"limit": "800", "cmd": "asyncGetTableGUI", "cmdMode": "asynch"}
url = url_set_query_params(url, query_params) url = url_set_query_params(url, query_params)
log.explain("Found ILIAS redirection page, following it as a new entry") log.explain("Found ILIAS video frame page, fetching actual content next")
return [IliasPageElement(IliasElementType.VIDEO_FOLDER_MAYBE_PAGINATED, url, "")] return [IliasPageElement(IliasElementType.VIDEO_FOLDER_MAYBE_PAGINATED, url, "")]
is_paginated = self._soup.find(id=re.compile(r"tab_page_sel.+")) is not None is_paginated = self._soup.find(id=re.compile(r"tab_page_sel.+")) is not None
@ -205,7 +205,7 @@ class IliasPage:
video_url = self._abs_url_from_link(link) video_url = self._abs_url_from_link(link)
log.explain(f"Found video {video_name!r} at {video_url!r}") log.explain(f"Found video {video_name!r} at {video_url}")
return IliasPageElement(IliasElementType.VIDEO_PLAYER, video_url, video_name, modification_time) return IliasPageElement(IliasElementType.VIDEO_PLAYER, video_url, video_name, modification_time)
def _find_exercise_entries(self) -> List[IliasPageElement]: def _find_exercise_entries(self) -> List[IliasPageElement]:
@ -436,7 +436,7 @@ class IliasPage:
_unexpected_html_warning() _unexpected_html_warning()
log.warn_contd( log.warn_contd(
f"Tried to figure out element type, but failed for {str(element_name)!r} / {link_element!r})" f"Tried to figure out element type, but failed for {element_name!r} / {link_element!r})"
) )
return None return None

4
PFERD/crawl/ilias/kit_ilias_web_crawler.py
View File

@ -243,11 +243,11 @@ class KitIliasWebCrawler(HttpCrawler):
elements.clear() elements.clear()
async with cl: async with cl:
next_stage_url: Optional[str] = url next_stage_url: Optional[str] = url
log.explain_topic(f"Parsing HTML page for {fmt_path(path)}")
while next_stage_url: while next_stage_url:
soup = await self._get_page(next_stage_url) soup = await self._get_page(next_stage_url)
log.explain(f"URL: {url}") log.explain_topic(f"Parsing HTML page for {fmt_path(path)}")
log.explain(f"URL: {next_stage_url}")
page = IliasPage(soup, url, parent) page = IliasPage(soup, url, parent)
next_stage_url = page.get_next_stage_url() next_stage_url = page.get_next_stage_url()