Skip to content

parse_ind

topic_segmentation.news_dataset.parse_ind

Extract editorial sections from saved Independent pages.

is_noise_heading(text: str) -> bool

Source code in src/topic_segmentation/news_dataset/parse_ind.py
69
70
71
def is_noise_heading(text: str) -> bool:
    t = text.lower().strip()
    return len(t) < 3 or any(pat in t for pat in NOISE_PATTERNS)

is_skip_container(el) -> bool

Source code in src/topic_segmentation/news_dataset/parse_ind.py
74
75
76
77
78
79
80
def is_skip_container(el) -> bool:
    if el.name in ("aside", "nav", "form"):
        return True
    cls = set(el.get("class") or [])
    if cls & SKIP_DIV_CLASSES:
        return True
    return False

is_trailing_element(el) -> bool

Source code in src/topic_segmentation/news_dataset/parse_ind.py
83
84
85
86
87
88
89
90
91
def is_trailing_element(el) -> bool:
    if el.name in ("h2", "h3", "h4"):
        t = el.get_text(" ", strip=True).lower().rstrip(":")
        if t in TRAILING_HEADINGS:
            return True
    text_lower = el.get_text(" ", strip=True).lower()
    if any(text_lower.startswith(p) for p in TRAILING_TEXT_PREFIXES):
        return True
    return False

collect_elements(container) -> list

Collect content elements from the article body.

Source code in src/topic_segmentation/news_dataset/parse_ind.py
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
def collect_elements(container) -> list:
    """Collect content elements from the article body."""
    elements = []
    for el in container.children:
        if not hasattr(el, "name") or el.name is None:
            continue
        if is_skip_container(el):
            continue

        cls = set(el.get("class") or [])

        # Section subheading div or content list wrapped in sc-kk992l-0
        if el.name == "div" and "sc-kk992l-0" in cls:
            inner_list = el.find(["ul", "ol"])
            inner_head = el.find(["h2", "h3", "h4"])
            if inner_list and not inner_head:
                # Include content lists and skip link-only "Read more" lists.
                if not is_link_only_list(inner_list):
                    elements.append(inner_list)
            else:
                elements.append(el)
            continue

        # Image div (contains a figure with an actual image)
        if el.name == "div" and "image" in cls:
            fig = el.find("figure")
            if fig:
                img = fig.find("img")
                if img and (img.get("src") or "").startswith("http"):
                    elements.append(fig)
            continue

        if el.name in ("p", "ul", "ol", "blockquote"):
            if not is_link_only_list(el):
                elements.append(el)
            continue

        # Skip unrecognized divs, including ads and empty wrappers.

    return elements

process_article(aid: str, raw_html: str, meta: dict)

Source code in src/topic_segmentation/news_dataset/parse_ind.py
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
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
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

    # Article header (inside article, contains title/standfirst/hero)
    art_header = article.find("header")

    h1 = art_header.find("h1") if art_header else article.find("h1")
    title = h1.get_text(" ", strip=True) if h1 else meta.get("title", "")

    # Standfirst: h2.sc-1cmj4ml-0 inside article header
    standfirst_text = None
    if art_header:
        sf = art_header.find("h2", class_=lambda c: c and "sc-1cmj4ml-0" in c)
        if sf:
            text = sf.get_text(" ", strip=True)
            if text and not text.lower().startswith("sign up"):
                standfirst_text = text

    # Hero image from article header figure
    hero_img_src = None
    hero_img_cap = None
    if art_header:
        fig = art_header.find("figure")
        if fig:
            img = fig.find("img")
            if img and (img.get("src") or "").startswith("http"):
                hero_img_src = img["src"]
                figcap = fig.find("figcaption")
                if figcap:
                    hero_img_cap = figcap.get_text(" ", strip=True)

    main_wrapper = article.find("div", class_=lambda c: c and "main-wrapper" in c)
    if not main_wrapper:
        return None
    content = main_wrapper.find("div", class_=lambda c: c and "sc-jbiisr-0" in c)
    if not content:
        return None

    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:
        cap_html = f"<figcaption>{hero_img_cap}</figcaption>" if hero_img_cap else ""
        sentences.append(hero_img_cap or "")
        html_parts.append({"tag": "figure", "html": f'<img src="{hero_img_src}" style="max-width:100%">{cap_html}'})
        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

        # Section subheading div (sc-kk992l-0)
        if el.name == "div" and "sc-kk992l-0" in set(el.get("class") or []):
            text = el.get_text(" ", strip=True)
            if not text or is_noise_heading(text):
                continue
            if len(text) > 200:
                continue
            inner_head = el.find(["h2", "h3", "h4"])
            tag = inner_head.name if inner_head else "h3"
            sentences.append(text)
            html_parts.append({"tag": tag, "html": text})
            labels.append(0 if first_elem else 1)
            title_labels.append(1)
            first_elem = False
            continue

        text = el.get_text(" ", strip=True)
        if not text:
            continue

        if any(text.lower().startswith(p) for p in SKIP_PARA_PREFIXES):
            continue

        sentences.append(text)
        html_parts.append({"tag": el.name, "html": clean_inner_html(el, "https://www.independent.co.uk")})
        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": "Independent",
        "title": title,
        "url": meta.get("url", ""),
        "sentences": sentences,
        "html_parts": html_parts,
        "labels": labels,
        "title_labels": title_labels,
        "num_sections": labels.count(1) + 1,
    }

main()

Source code in src/topic_segmentation/news_dataset/parse_ind.py
268
269
270
def main():
    articles = read_articles("independent_subheadings", process_article)
    write_articles("ind_segments.json", unique_articles(articles))