Skip to content

sys_sec_scrape

src.scrapers.sys_sec_scrape

check_url_cached(url: str, ttl: int = CACHE_TTL_URL) -> bool

Check if a URL exists, with disk caching.

Returns True/False. Positive results are cached for ttl seconds; negative results are cached for CACHE_TTL_URL_NEG (shorter) so they are re-checked periodically without hammering every run.

Source code in src/scrapers/sys_sec_scrape.py 
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
def check_url_cached(url: str, ttl: int = CACHE_TTL_URL) -> bool:
    """Check if a URL exists, with disk caching.

    Returns True/False.  Positive results are cached for ``ttl`` seconds;
    negative results are cached for CACHE_TTL_URL_NEG (shorter) so they
    are re-checked periodically without hammering every run.
    """
    cached = _read_cache(CACHE_DIR, url, ttl=ttl, namespace="url_exists")
    if cached is True:
        return True  # positive hit – trust it
    # Check negative cache (shorter TTL)
    cached_neg = _read_cache(CACHE_DIR, url, ttl=CACHE_TTL_URL_NEG, namespace="url_exists")
    if cached_neg is False:
        return False  # recently confirmed non-existent

    try:
        resp = _session.head(url, allow_redirects=True, timeout=10)
        if resp.status_code == 429:
            time.sleep(10)
            resp = _session.head(url, allow_redirects=True, timeout=10)
        exists = 200 <= resp.status_code < 300
    except requests.RequestException as e:
        logger.error(f"  Request error for {url}: {e}")
        # Network errors (timeouts, DNS failures, connection refused) are
        # transient — do NOT cache them as negative results.
        return False

    _write_cache(CACHE_DIR, url, exists, namespace="url_exists")
    return exists

cached_github_stats(url: str, ttl: int = CACHE_TTL_STATS) -> dict[str, Any]

Fetch GitHub repo stats with caching, ETags, and rate-limit handling.

Uses conditional requests (If-None-Match) so that 304 responses do NOT count against the GitHub API rate limit. This effectively makes re-runs free for repos whose data hasn't changed.

Source code in src/scrapers/sys_sec_scrape.py 
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
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
def cached_github_stats(url: str, ttl: int = CACHE_TTL_STATS) -> dict[str, Any]:
    """Fetch GitHub repo stats with caching, ETags, and rate-limit handling.

    Uses conditional requests (If-None-Match) so that 304 responses do NOT
    count against the GitHub API rate limit.  This effectively makes re-runs
    free for repos whose data hasn't changed.
    """
    cached = _read_cache(CACHE_DIR, url, ttl=ttl, namespace="github_stats")
    if cached is not _MISSING:
        return cached  # dict or None — still fresh

    repo = url.split("github.com/")[1]
    for suffix in ("/tree/", "/blob/", "/pkgs/", "/releases/", "/wiki", "/issues", "/pull/", "/commit/"):
        if suffix in repo:
            repo = repo.split(suffix)[0]
    # Keep only owner/repo (first two path segments)
    parts = repo.strip("/").split("/")
    repo = "/".join(parts[:2]).removesuffix(".git")

    headers = _github_headers()

    # Use stored ETag for conditional request (304 = free, no rate cost)
    entry = _read_cache_entry(CACHE_DIR, url, namespace="github_stats")
    if entry and entry.get("etag"):
        headers["If-None-Match"] = entry["etag"]

    try:
        resp = _session.get(f"https://api.github.com/repos/{repo}", headers=headers, timeout=_session.default_timeout)
        if resp.status_code == 403 and "rate limit" in resp.text.lower():
            reset_time = int(resp.headers.get("X-RateLimit-Reset", 0))
            wait = max(reset_time - int(time.time()), 0) + 5
            logger.info(f"  Rate limited. Waiting {wait}s for reset...")
            time.sleep(wait)
            resp = _session.get(
                f"https://api.github.com/repos/{repo}", headers=headers, timeout=_session.default_timeout
            )

        if resp.status_code == 304 and entry:
            # Data unchanged — refresh timestamp, return cached data (free!)
            _refresh_cache_ts(CACHE_DIR, url, namespace="github_stats")
            return entry.get("body")
        if resp.status_code == 200:
            d = resp.json()
            result = {
                "github_forks": d.get("forks_count", 0),
                "github_stars": d.get("stargazers_count", 0),
                "updated_at": d.get("updated_at", "NA"),
                "created_at": d.get("created_at", "NA"),
                "pushed_at": d.get("pushed_at", "NA"),
                "name": d.get("full_name", "NA"),
                "description": d.get("description", ""),
                "language": d.get("language", ""),
                "license": (d.get("license") or {}).get("spdx_id", ""),
                "topics": d.get("topics", []),
            }
            etag = resp.headers.get("ETag")
            _write_cache(CACHE_DIR, url, result, namespace="github_stats", etag=etag)
            return result
        logger.warning(f"  Could not collect GitHub stats for {url} (HTTP {resp.status_code})")
    except requests.RequestException as e:
        logger.warning(f"  GitHub request error for {url}: {e}")
    result = None
    _write_cache(CACHE_DIR, url, result, namespace="github_stats")
    return result

cached_zenodo_stats(url: str, ttl: int = CACHE_TTL_STATS) -> dict[str, Any]

Fetch Zenodo record stats with caching and 429 retry.

Source code in src/scrapers/sys_sec_scrape.py 
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
def cached_zenodo_stats(url: str, ttl: int = CACHE_TTL_STATS) -> dict[str, Any]:
    """Fetch Zenodo record stats with caching and 429 retry."""
    cached = _read_cache(CACHE_DIR, url, ttl=ttl, namespace="zenodo_stats")
    if cached is not _MISSING:
        return cached

    if "/records/" in url:
        rec = url.split("/records/")[-1]
    elif "/record/" in url:
        rec = url.split("/record/")[-1]
    elif "zenodo." in url:
        rec = url.split("zenodo.")[-1]
    else:
        logger.info(f"  Could not parse Zenodo URL {url}")
        return None

    # Strip fragments (#...) and query strings (?...)
    rec = rec.split("#")[0].split("?")[0].strip("/")

    result = None
    try:
        for attempt in range(4):  # up to 3 retries on 429
            resp = _session.get(f"https://zenodo.org/api/records/{rec}", timeout=_session.default_timeout)
            if resp.status_code == 200:
                record = resp.json()
                stats = record.get("stats", {})
                result = {
                    "zenodo_views": stats.get("unique_views", 0),
                    "zenodo_downloads": stats.get("unique_downloads", 0),
                    "updated_at": record.get("updated", ""),
                    "created_at": record.get("created", ""),
                }
                break
            if resp.status_code == 429:
                retry_after = int(resp.headers.get("Retry-After", 0))
                wait = max(retry_after, 2 ** (attempt + 1))  # exponential backoff: 2, 4, 8s
                logger.info(f"  Zenodo 429 for {url}, waiting {wait}s (attempt {attempt + 1}/4)")
                time.sleep(wait)
            else:
                logger.info(f"  Could not collect Zenodo stats for {url} (HTTP {resp.status_code})")
                break
    except requests.RequestException as e:
        logger.error(f"  Zenodo request error for {url}: {e}")

    _write_cache(CACHE_DIR, url, result, namespace="zenodo_stats")
    return result

cached_figshare_stats(url, ttl=CACHE_TTL_STATS)

Fetch Figshare article stats with caching.

Source code in src/scrapers/sys_sec_scrape.py 
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
def cached_figshare_stats(url, ttl=CACHE_TTL_STATS):
    """Fetch Figshare article stats with caching."""
    cached = _read_cache(CACHE_DIR, url, ttl=ttl, namespace="figshare_stats")
    if cached is not _MISSING:
        return cached

    clean = url
    if clean.endswith((".v1", ".v2", ".v3", ".v4", ".v5", ".v6", ".v7", ".v8", ".v9")):
        clean = clean[:-3]
    article_id = clean.split("figshare.")[-1]

    views = downloads = -1
    updated = created = "NA"
    try:
        r = _session.get(
            f"https://stats.figshare.com/total/views/article/{article_id}", timeout=_session.default_timeout
        )
        if r.status_code == 200:
            views = r.json().get("totals", -1)
        r = _session.get(
            f"https://stats.figshare.com/total/downloads/article/{article_id}", timeout=_session.default_timeout
        )
        if r.status_code == 200:
            downloads = r.json().get("totals", -1)
        r = _session.get(f"https://api.figshare.com/v2/articles/{article_id}", timeout=_session.default_timeout)
        if r.status_code == 200:
            d = r.json()
            updated = d.get("modified_date", "NA")
            created = d.get("created_date", "NA")
    except requests.RequestException as e:
        logger.error(f"  Figshare request error for {url}: {e}")

    result = {
        "figshare_views": views,
        "figshare_downloads": downloads,
        "updated_at": updated,
        "created_at": created,
    }
    _write_cache(CACHE_DIR, url, result, namespace="figshare_stats")
    return result