Determine cover image file extension from response header

Fixes #29 Add User-Agent to fix 403 Client Error When no User-Agent is provided, Wikipedia returns a 403 status code: requests.exceptions.HTTPError: 403 Client Error: Forbidden. Please comply with the User-Agent policy: https://meta.wikimedia.org/wiki/User-Agent_policy for url: https://upload.wikimedia.org/wikipedia/commons/3/3f/JPEG_example_flower.jpg
ptrstn · Mar 13, 2022 · dc39500 · dc39500
1 parent a21ccd9
commit dc39500
Show file tree

Hide file tree

Showing 3 changed files with 51 additions and 11 deletions.
diff --git a/dailyblink/core.py b/dailyblink/core.py
@@ -7,6 +7,7 @@
 import cloudscraper
 from bs4 import BeautifulSoup
 from cloudscraper import CloudflareChallengeError
+from requests import Response
 
 from dailyblink.media import (
     set_m4a_meta_data,
@@ -15,7 +16,7 @@
 )
 from dailyblink.settings import (
     BASE_URL,
-    COVER_FILE_NAME,
+    COVER_FILE_NAME_STEM,
     PLAYLIST_FILE_NAME,
     LANGUAGES,
     MAX_CLOUDFLARE_ATTEMPTS,
@@ -75,22 +76,23 @@ def _download_daily_blinks(self, language_code, base_path):
         valid_author = re.sub(r"([^\s\w]|_)+", "", blink_info["author"])
         book_path = base_path / language / f"{date.today()} - {valid_title}"
 
-        print("Saving book text...")
-        markdown_text = _create_markdown_text(blink_info, chapters)
-        markdown_book_path = book_path / f"{valid_title} - {valid_author}.md"
-        save_text(text=markdown_text, file_path=markdown_book_path)
-
         print("Saving book cover...")
         cover_response = self.scraper.get(blink_info["cover_url"])
+        file_extension = _determine_file_extension(cover_response)
         cover = cover_response.content
-        cover_path = book_path / COVER_FILE_NAME
+        cover_path = book_path / f"{COVER_FILE_NAME_STEM}.{file_extension}"
         save_media(media=cover, file_path=cover_path)
 
+        print("Saving book text...")
+        markdown_text = _create_markdown_text(blink_info, chapters, cover_path)
+        markdown_book_path = book_path / f"{valid_title} - {valid_author}.md"
+        save_text(text=markdown_text, file_path=markdown_book_path)
+
         try:
             file_list = []
             for number, chapter_id in enumerate(chapter_ids):
                 status = f"Saving audio track #{number + 1} - {chapters[number][0]}"
-                status_limited = f"{status[:MAX_LINE_LENGTH-3]}..."
+                status_limited = f"{status[:MAX_LINE_LENGTH - 3]}..."
                 print(status_limited)
                 file_name = f"{number:02d} - {valid_title}.m4a"
                 file_path = book_path / file_name
@@ -191,7 +193,7 @@ def _create_blink_info(response_text):
     }
 
 
-def _create_markdown_text(blink_info, chapters, cover_path=COVER_FILE_NAME):
+def _create_markdown_text(blink_info, chapters, cover_path):
     markdown_text = f"# {blink_info['title']}\n\n"
     markdown_text += f"_{blink_info['author']}_\n\n"
     markdown_text += f"{blink_info['read_time']}\n\n"
@@ -210,3 +212,10 @@ def _create_markdown_text(blink_info, chapters, cover_path=COVER_FILE_NAME):
 
     markdown_text += f"Source: {blink_info['url']}\n\n"
     return markdown_text
+
+
+def _determine_file_extension(cover_response: Response) -> str:
+    headers = cover_response.headers
+    content_type = headers["content-type"]
+    _, file_extension = content_type.split("/")
+    return file_extension
diff --git a/dailyblink/settings.py b/dailyblink/settings.py
@@ -2,7 +2,7 @@
 
 BASE_URL = "https://www.blinkist.com"
 
-COVER_FILE_NAME = "cover.jpg"
+COVER_FILE_NAME_STEM = "cover"
 PLAYLIST_FILE_NAME = "playlist.m3u"
 BLINKS_DEFAULT_PATH = pathlib.Path.home() / "Musik"
 BLINKS_DIR_NAME = "blinks"

diff --git a/tests/test_core.py b/tests/test_core.py
@@ -1,9 +1,12 @@
 import pathlib
 
+import requests
+
 from dailyblink.core import (
     save_media,
     BlinkistScraper,
     _create_markdown_text,
+    _determine_file_extension,
 )
 from dailyblink.media import save_text
 
@@ -73,5 +76,33 @@ def test_save_book_text():
     blink_info = blinkist_scraper._get_daily_blink_info(language="de")
     blink_url = blink_info["url"]
     chapters = blinkist_scraper._request_blinkist_book_text(blink_url)["chapters"]
-    markdown_text = _create_markdown_text(blink_info, chapters)
+    markdown_text = _create_markdown_text(
+        blink_info, chapters, "test_output/cover.jpeg"
+    )
     save_text(markdown_text, file_path="test_output/daily_blink.md")
+
+
+def test_determine_file_extension():
+    headers = {
+        "user-agent": (
+            "Mozilla/5.0 (X11; Linux x86_64) "
+            "AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/98.0.4758.80 Safari/537.36"
+        ),
+    }
+
+    jpg_url = (
+        "https://upload.wikimedia.org/wikipedia/commons/3/3f/JPEG_example_flower.jpg"
+    )
+    jpg_response = requests.get(jpg_url, headers=headers)
+    assert _determine_file_extension(jpg_response) == "jpeg"
+
+    png_url = "https://upload.wikimedia.org/wikipedia/de/b/bb/Png-logo.png"
+    png_response = requests.get(png_url, headers=headers)
+    assert _determine_file_extension(png_response) == "png"
+
+    cover_url = (
+        "https://images.blinkist.io/images/books/5e48b5726cee070006209356/1_1/470.jpg"
+    )
+    cover_response = requests.get(cover_url, headers=headers)
+    assert _determine_file_extension(cover_response) == "png"