diff options
| author | Florian Dold <florian@dold.me> | 2021-05-11 19:16:04 +0200 |
|---|---|---|
| committer | Florian Dold <florian@dold.me> | 2021-05-11 19:16:04 +0200 |
| commit | 2b72c7f57d318271856f992eb2e58c133ae5179e (patch) | |
| tree | 9798186e896ae41497f7389153626d9055266ad8 | |
| parent | ebfd9c60d0e59f6373309ac96d8abf6094ceefb9 (diff) | |
| download | www_shared-2b72c7f57d318271856f992eb2e58c133ae5179e.tar.gz www_shared-2b72c7f57d318271856f992eb2e58c133ae5179e.zip | |
extract only article content
| -rw-r--r-- | sitegen/site.py | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/sitegen/site.py b/sitegen/site.py index f9d3e7d..2148763 100644 --- a/sitegen/site.py +++ b/sitegen/site.py | |||
| @@ -65,14 +65,14 @@ def cut_text(filename, count): | |||
| 65 | return textreduced | 65 | return textreduced |
| 66 | 66 | ||
| 67 | 67 | ||
| 68 | def extract_body(text): | 68 | def extract_body(text, content_id="newspost-content"): |
| 69 | """Extract the body of some HTML and | 69 | """Extract the body of some HTML and |
| 70 | return it wrapped in an <article> tag.""" | 70 | return it wrapped in an <article> tag.""" |
| 71 | soup = BeautifulSoup(text, features="lxml") | 71 | soup = BeautifulSoup(text, features="lxml") |
| 72 | bs = soup.findAll("body") | 72 | content = soup.find(id=content_id) |
| 73 | b = bs[0] | 73 | if content is None: |
| 74 | b.name = "article" | 74 | raise Error("can't extract content") |
| 75 | return b.prettify() | 75 | return content.prettify() |
| 76 | 76 | ||
| 77 | 77 | ||
| 78 | def make_helpers(root, in_file, locale): | 78 | def make_helpers(root, in_file, locale): |