diff options
Diffstat (limited to 'gallery_dl/extractor/flickr.py')
| -rw-r--r-- | gallery_dl/extractor/flickr.py | 112 |
1 files changed, 79 insertions, 33 deletions
diff --git a/gallery_dl/extractor/flickr.py b/gallery_dl/extractor/flickr.py index e85a375..eb68c3e 100644 --- a/gallery_dl/extractor/flickr.py +++ b/gallery_dl/extractor/flickr.py @@ -23,13 +23,10 @@ class FlickrExtractor(Extractor): request_interval = (1.0, 2.0) request_interval_min = 0.5 - def __init__(self, match): - Extractor.__init__(self, match) - self.item_id = match.group(1) - def _init(self): self.api = FlickrAPI(self) self.user = None + self.item_id = self.groups[0] def items(self): data = self.metadata() @@ -51,6 +48,8 @@ class FlickrExtractor(Extractor): def metadata(self): """Return general metadata""" self.user = self.api.urls_lookupUser(self.item_id) + if self.config("profile", False): + self.user.update(self.api.people_getInfo(self.user["nsid"])) return {"user": self.user} def photos(self): @@ -75,23 +74,26 @@ class FlickrImageExtractor(FlickrExtractor): r"|flic\.kr/p/([A-Za-z1-9]+))") example = "https://www.flickr.com/photos/USER/12345" - def __init__(self, match): - FlickrExtractor.__init__(self, match) - if not self.item_id: + def items(self): + item_id, enc_id = self.groups + if enc_id is not None: alphabet = ("123456789abcdefghijkmnopqrstu" "vwxyzABCDEFGHJKLMNPQRSTUVWXYZ") - self.item_id = util.bdecode(match.group(2), alphabet) + item_id = util.bdecode(enc_id, alphabet) - def items(self): - photo = self.api.photos_getInfo(self.item_id) + photo = self.api.photos_getInfo(item_id) - self.api._extract_metadata(photo) + self.api._extract_metadata(photo, False) if photo["media"] == "video" and self.api.videos: self.api._extract_video(photo) else: self.api._extract_photo(photo) - photo["user"] = photo["owner"] + if self.config("profile", False): + photo["user"] = self.api.people_getInfo(photo["owner"]["nsid"]) + else: + photo["user"] = photo["owner"] + photo["title"] = photo["title"]["_content"] photo["comments"] = text.parse_int(photo["comments"]["_content"]) photo["description"] = photo["description"]["_content"] @@ -120,11 +122,8 @@ class FlickrAlbumExtractor(FlickrExtractor): pattern = BASE_PATTERN + r"/photos/([^/?#]+)/(?:album|set)s(?:/(\d+))?" example = "https://www.flickr.com/photos/USER/albums/12345" - def __init__(self, match): - FlickrExtractor.__init__(self, match) - self.album_id = match.group(2) - def items(self): + self.album_id = self.groups[1] if self.album_id: return FlickrExtractor.items(self) return self._album_items() @@ -163,12 +162,9 @@ class FlickrGalleryExtractor(FlickrExtractor): pattern = BASE_PATTERN + r"/photos/([^/?#]+)/galleries/(\d+)" example = "https://www.flickr.com/photos/USER/galleries/12345/" - def __init__(self, match): - FlickrExtractor.__init__(self, match) - self.gallery_id = match.group(2) - def metadata(self): data = FlickrExtractor.metadata(self) + self.gallery_id = self.groups[1] data["gallery"] = self.api.galleries_getInfo(self.gallery_id) return data @@ -223,13 +219,10 @@ class FlickrSearchExtractor(FlickrExtractor): pattern = BASE_PATTERN + r"/search/?\?([^#]+)" example = "https://flickr.com/search/?text=QUERY" - def __init__(self, match): - FlickrExtractor.__init__(self, match) - self.search = text.parse_query(match.group(1)) + def metadata(self): + self.search = text.parse_query(self.groups[0]) if "text" not in self.search: self.search["text"] = "" - - def metadata(self): return {"search": self.search} def photos(self): @@ -275,13 +268,27 @@ class FlickrAPI(oauth.OAuth1API): "appletv" : 1, "iphone_wifi": 0, } + LICENSES = { + "0": "All Rights Reserved", + "1": "Attribution-NonCommercial-ShareAlike License", + "2": "Attribution-NonCommercial License", + "3": "Attribution-NonCommercial-NoDerivs License", + "4": "Attribution License", + "5": "Attribution-ShareAlike License", + "6": "Attribution-NoDerivs License", + "7": "No known copyright restrictions", + "8": "United States Government Work", + "9": "Public Domain Dedication (CC0)", + "10": "Public Domain Mark", + } def __init__(self, extractor): oauth.OAuth1API.__init__(self, extractor) - self.exif = extractor.config("exif", False) self.videos = extractor.config("videos", True) - self.contexts = extractor.config("contexts", False) + self.meta_exif = extractor.config("exif", False) + self.meta_info = extractor.config("info", False) + self.meta_contexts = extractor.config("contexts", False) self.maxsize = extractor.config("size-max") if isinstance(self.maxsize, str): @@ -321,6 +328,26 @@ class FlickrAPI(oauth.OAuth1API): params = {"group_id": group_id} return self._pagination("groups.pools.getPhotos", params) + def people_getInfo(self, user_id): + """Get information about a user.""" + params = {"user_id": user_id} + user = self._call("people.getInfo", params) + + try: + user = user["person"] + for key in ("description", "username", "realname", "location", + "profileurl", "photosurl", "mobileurl"): + if isinstance(user.get(key), dict): + user[key] = user[key]["_content"] + photos = user["photos"] + for key in ("count", "firstdate", "firstdatetaken"): + if isinstance(photos.get(key), dict): + photos[key] = photos[key]["_content"] + except Exception: + pass + + return user + def people_getPhotos(self, user_id): """Return photos from the given user's photostream.""" params = {"user_id": user_id} @@ -469,14 +496,15 @@ class FlickrAPI(oauth.OAuth1API): self._extract_metadata(photo) photo["id"] = text.parse_int(photo["id"]) - if "owner" in photo: + if "owner" not in photo: + photo["owner"] = self.extractor.user + elif not self.meta_info: photo["owner"] = { "nsid" : photo["owner"], "username" : photo["ownername"], "path_alias": photo["pathalias"], } - else: - photo["owner"] = self.extractor.user + del photo["pathalias"] del photo["ownername"] @@ -522,8 +550,23 @@ class FlickrAPI(oauth.OAuth1API): photo["width"] = photo["height"] = 0 return photo - def _extract_metadata(self, photo): - if self.exif: + def _extract_metadata(self, photo, info=True): + if info and self.meta_info: + try: + photo.update(self.photos_getInfo(photo["id"])) + photo["title"] = photo["title"]["_content"] + photo["comments"] = text.parse_int( + photo["comments"]["_content"]) + photo["description"] = photo["description"]["_content"] + photo["tags"] = [t["raw"] for t in photo["tags"]["tag"]] + photo["views"] = text.parse_int(photo["views"]) + photo["id"] = text.parse_int(photo["id"]) + except Exception as exc: + self.log.warning( + "Unable to retrieve 'info' data for %s (%s: %s)", + photo["id"], exc.__class__.__name__, exc) + + if self.meta_exif: try: photo.update(self.photos_getExif(photo["id"])) except Exception as exc: @@ -531,7 +574,7 @@ class FlickrAPI(oauth.OAuth1API): "Unable to retrieve 'exif' data for %s (%s: %s)", photo["id"], exc.__class__.__name__, exc) - if self.contexts: + if self.meta_contexts: try: photo.update(self.photos_getAllContexts(photo["id"])) except Exception as exc: @@ -539,6 +582,9 @@ class FlickrAPI(oauth.OAuth1API): "Unable to retrieve 'contexts' data for %s (%s: %s)", photo["id"], exc.__class__.__name__, exc) + if "license" in photo: + photo["license_name"] = self.LICENSES.get(photo["license"]) + @staticmethod def _clean_info(info): info["title"] = info["title"]["_content"] |