diff options
| author | Pinapelz <yukais@pinapelz.com> | 2025-05-27 15:54:20 -0700 |
|---|---|---|
| committer | Pinapelz <yukais@pinapelz.com> | 2025-05-27 15:54:20 -0700 |
| commit | 8d4a3eeb3a68e39301caec1b2289783bd2bf7b6d (patch) | |
| tree | 8c9d9e950d2829081858507ae1b079d80aaab481 /bandai_namco | |
| parent | bf38127abdaf5323391ae00f5134020ebb01c907 (diff) | |
wmmt: continue adding text until minimum char length is exceeded
Diffstat (limited to 'bandai_namco')
| -rw-r--r-- | bandai_namco/wmmt.py | 21 |
1 files changed, 15 insertions, 6 deletions
diff --git a/bandai_namco/wmmt.py b/bandai_namco/wmmt.py index fc0e4bf..b7ea927 100644 --- a/bandai_namco/wmmt.py +++ b/bandai_namco/wmmt.py @@ -144,8 +144,11 @@ def make_wmmt_news_extractor(identifier: str, version: constants.WANGAN_MAXI_VER if paragraphs: content = paragraphs[0].get_text(" ", strip=True) if content and len(content.split()) < 50 and len(paragraphs) > 1: - next_p_content = paragraphs[1].get_text(" ", strip=True) - content += " " + next_p_content + for paragraph in paragraphs[1:]: + next_p_content = paragraph.get_text(" ", strip=True) + content += " " + next_p_content + if len(content.split()) >= 50: + break images = [] seen_srcs = [] for img in container.find_all("img"): @@ -178,8 +181,11 @@ def make_wmmt_news_extractor(identifier: str, version: constants.WANGAN_MAXI_VER if paragraphs: content = paragraphs[0].get_text(" ", strip=True) if content and len(content.split()) < 50 and len(paragraphs) > 1: - next_p_content = paragraphs[1].get_text(" ", strip=True) - content += " " + next_p_content + for paragraph in paragraphs[1:]: + next_p_content = paragraph.get_text(" ", strip=True) + content += " " + next_p_content + if len(content.split()) >= 50: + break images = [] seen_srcs = [] for img in container.select("img"): @@ -214,8 +220,11 @@ def make_wmmt_news_extractor(identifier: str, version: constants.WANGAN_MAXI_VER if paragraphs: content = paragraphs[0].get_text(" ", strip=True) if content and len(content.split()) < 50 and len(paragraphs) > 1: - next_p_content = paragraphs[1].get_text(" ", strip=True) - content += " " + next_p_content + for paragraph in paragraphs[1:]: + next_p_content = paragraph.get_text(" ", strip=True) + content += " " + next_p_content + if len(content.split()) >= 50: + break images = [] seen_srcs = [] for img in container.select("img"): |