src/scrape_movies/constants.py

@@ -35,3 +35,6 @@ MOVIES_OUTPUT_FILE: str = "movies.txt"
 
 ## The saved copy of the course's Hacker News page, used offline.
 HACKER_NEWS_FIXTURE_PATH: Path = FIXTURES_DIR / "hacker_news.html"
+
+## The saved headings of the live Empire page, used offline.
+EMPIRE_FIXTURE_PATH: Path = FIXTURES_DIR / "empire_live_excerpt.html"

src/scrape_movies/infrastructure/empire_movies.py

@@ -0,0 +1,55 @@
+"""@brief Reading the movie titles from the Empire "100 Greatest Movies" page."""
+
+import re
+
+from bs4 import Tag
+
+from scrape_movies.infrastructure.soup_basics import make_soup
+
+## The 2020 page (the assignment's snapshot): `<h3 class="title">100) Title</h3>`.
+SNAPSHOT_TITLE = "h3.title"
+## The current page: `<h2><strong>100) Title (year)</strong></h2>`.
+_RANKED_HEADING = re.compile(r"^\s*\d{1,3}\)")
+
+
+def parse_titles(html: str) -> list[str]:
+    """@brief Read the movie titles in page order.
+
+    The assignment's snapshot is read through `h3.title`. When the page has no
+    such tag, as on the current live page, the `h2` headings that start with a
+    rank such as `100)` are used.
+
+    @param html The HTML of the page.
+    @return The titles in page order, each as the page shows it.
+    """
+    soup = make_soup(html)
+    titles = [tag.get_text().strip() for tag in soup.select(SNAPSHOT_TITLE)]
+    if titles:
+        return titles
+    headings = [tag for tag in soup.find_all("h2") if isinstance(tag, Tag)]
+    return [
+        text
+        for text in (heading.get_text().strip() for heading in headings)
+        if _RANKED_HEADING.match(text)
+    ]
+
+
+def first_title_markup(html: str) -> str:
+    """@brief Show the markup of the first title, as seen with "Inspect".
+
+    @param html The HTML of the page.
+    @return The indented HTML of the first title tag, or "" when there is none.
+    """
+    soup = make_soup(html)
+    tag = soup.select_one(SNAPSHOT_TITLE)
+    if tag is None:
+        tag = next(
+            (
+                heading
+                for heading in soup.find_all("h2")
+                if isinstance(heading, Tag)
+                and _RANKED_HEADING.match(heading.get_text())
+            ),
+            None,
+        )
+    return str(tag.prettify()).rstrip() if tag is not None else ""