116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225 | def process_article(aid: str, raw_html: str, meta: dict):
soup = BeautifulSoup(ftfy.fix_text(raw_html), "html.parser")
article = soup.find("article")
if not article:
return None
content = article.find("div", class_="article-content")
if not content:
return None
h1 = article.find("h1")
title = h1.get_text(" ", strip=True) if h1 else meta.get("title", "")
# Standfirst from header excerpt
standfirst_text = None
header = article.find("header")
if header:
excerpt = header.find(class_="inews__post-excerpt")
if excerpt:
standfirst_text = excerpt.get_text(" ", strip=True)
# Hero image from header figure
hero_img_src = None
if header:
fig = header.find("figure", class_="inews__post-header__media")
if fig:
img = fig.find("img")
if img:
hero_img_src = img.get("src", "")
sentences, html_parts, labels, title_labels = [], [], [], []
if standfirst_text:
sentences.append(standfirst_text)
html_parts.append({"tag": "p", "html": standfirst_text})
labels.append(0)
title_labels.append(1)
if hero_img_src:
sentences.append("")
html_parts.append({"tag": "figure", "html": f'<img src="{hero_img_src}" style="max-width:100%">'})
labels.append(0)
title_labels.append(0)
first_elem = not (standfirst_text or hero_img_src)
for el in collect_elements(content):
if is_trailing_element(el):
break
if el.name == "figure":
img = el.find("img")
if not img:
continue
src = img.get("src", "")
if not src:
continue
figcap = el.find("figcaption")
cap_text = figcap.get_text(" ", strip=True) if figcap else ""
cap_html = f"<figcaption>{cap_text}</figcaption>" if cap_text else ""
sentences.append(cap_text)
html_parts.append({"tag": "figure", "html": f'<img src="{src}" style="max-width:100%">{cap_html}'})
labels.append(0)
title_labels.append(0)
first_elem = False
continue
text = el.get_text(" ", strip=True)
if not text:
continue
if el.name in ("h2", "h3", "h4") and is_noise_heading(text):
continue
if el.name == "p" and any(text.lower().startswith(p) for p in SKIP_PARA_PREFIXES):
continue
is_heading = el.name in ("h2", "h3", "h4") and len(text) <= 200
sentences.append(text)
html_parts.append({"tag": el.name, "html": clean_inner_html(el, "https://inews.co.uk")})
if is_heading:
labels.append(0 if first_elem else 1)
title_labels.append(1)
else:
labels.append(0)
title_labels.append(0)
first_elem = False
# Remove trailing headings without following content.
while sentences and title_labels[-1] == 1:
sentences.pop()
html_parts.pop()
labels.pop()
title_labels.pop()
if not sentences:
return None
return {
"articleId": aid,
"outlet": "INews",
"title": title,
"url": meta.get("url", ""),
"sentences": sentences,
"html_parts": html_parts,
"labels": labels,
"title_labels": title_labels,
"num_sections": labels.count(1) + 1,
}
|