diff options
Diffstat (limited to 'src/scrape_lexicanum.py')
| -rw-r--r-- | src/scrape_lexicanum.py | 21 |
1 files changed, 16 insertions, 5 deletions
diff --git a/src/scrape_lexicanum.py b/src/scrape_lexicanum.py index 20bc0da..34e9726 100644 --- a/src/scrape_lexicanum.py +++ b/src/scrape_lexicanum.py @@ -52,12 +52,12 @@ def get_page_content(config, page_name): parser_output = soup.find(id="mw-content-text").contents[0] - for unwanted in parser_output.select("table"): + for unwanted in parser_output.select("div.portal"): + unwanted.decompose() + for unwanted in parser_output.select("table.nottemplate"): + unwanted.decompose() + for unwanted in parser_output.select("table.Anpassen"): unwanted.decompose() - - content = parser_output.find("p") - for a in content.findAll("a"): - fix_link(config, a, "href") image = parser_output.find("a", {"class": "image"}) image_link = None @@ -66,6 +66,17 @@ def get_page_content(config, page_name): fix_link(config, image.contents[0], "src") image_link = image.contents[0]["src"] + for unwanted in parser_output.select("div.quotebox"): + unwanted.decompose() + for unwanted in parser_output.select("p > br"): + unwanted.parent.decompose() + for unwanted in parser_output.select("table"): + unwanted.decompose() + + content = parser_output.find("p") + for a in content.findAll("a"): + fix_link(config, a, "href") + header_md = markdownify(str(soup.find(id="firstHeading").contents[0])) content_md = markdownify(str(content)) |