diff options
Diffstat (limited to 'gallery_dl/extractor/patreon.py')
| -rw-r--r-- | gallery_dl/extractor/patreon.py | 46 |
1 files changed, 34 insertions, 12 deletions
diff --git a/gallery_dl/extractor/patreon.py b/gallery_dl/extractor/patreon.py index 18c10a6..570bd72 100644 --- a/gallery_dl/extractor/patreon.py +++ b/gallery_dl/extractor/patreon.py @@ -47,8 +47,8 @@ class PatreonExtractor(Extractor): self._attachments(post), self._content(post), ): - fhash = url.split("/")[9].partition("?")[0] - if fhash not in hashes: + fhash = self._filehash(url) + if fhash not in hashes or not fhash: hashes.add(fhash) post["hash"] = fhash post["type"] = kind @@ -158,12 +158,23 @@ class PatreonExtractor(Extractor): return attr def _filename(self, url): - """Fetch filename from its Content-Disposition header""" + """Fetch filename from an URL's Content-Disposition header""" response = self.request(url, method="HEAD", fatal=False) cd = response.headers.get("Content-Disposition") return text.extract(cd, 'filename="', '"')[0] @staticmethod + def _filehash(url): + """Extract MD5 hash from a download URL""" + parts = url.partition("?")[0].split("/") + parts.reverse() + + for part in parts: + if len(part) == 32: + return part + return "" + + @staticmethod def _build_url(endpoint, query): return ( "https://www.patreon.com/api/" + endpoint + @@ -194,7 +205,7 @@ class PatreonCreatorExtractor(PatreonExtractor): subcategory = "creator" pattern = (r"(?:https?://)?(?:www\.)?patreon\.com" r"/(?!(?:home|join|posts|login|signup)(?:$|[/?&#]))" - r"(?:user(?:/posts)?/?\?([^#]+)|([^/?&#]+)/?)") + r"([^/?&#]+)(?:/posts)?/?(?:\?([^#]+))?") test = ( ("https://www.patreon.com/koveliana", { "range": "1-25", @@ -213,6 +224,10 @@ class PatreonCreatorExtractor(PatreonExtractor): "title" : str, }, }), + ("https://www.patreon.com/koveliana/posts?filters[month]=2020-3", { + "count": 1, + "keyword": {"date": "dt:2020-03-30 21:21:44"}, + }), ("https://www.patreon.com/kovelianot", { "exception": exception.NotFoundError, }), @@ -222,26 +237,33 @@ class PatreonCreatorExtractor(PatreonExtractor): def __init__(self, match): PatreonExtractor.__init__(self, match) - self.query, self.creator = match.groups() + self.creator, self.query = match.groups() def posts(self): - if self.creator: - url = "{}/{}".format(self.root, self.creator.lower()) + query = text.parse_query(self.query) + + creator_id = query.get("u") + if creator_id: + url = "{}/user?u={}".format(self.root, creator_id) else: - query = text.parse_query(self.query) - url = "{}/user?u={}".format(self.root, query.get("u")) + url = "{}/{}".format(self.root, self.creator.lower()) page = self.request(url, notfound="creator").text campaign_id = text.extract(page, "/campaign/", "/")[0] - if not campaign_id: raise exception.NotFoundError("creator") + filters = "".join( + "&filter[{}={}".format(key[8:], text.escape(value)) + for key, value in query.items() + if key.startswith("filters[") + ) + url = self._build_url("posts", ( - "&sort=-published_at" + "&sort=" + query.get("sort", "-published_at") + "&filter[is_draft]=false" "&filter[contains_exclusive_posts]=true" - "&filter[campaign_id]=" + campaign_id + "&filter[campaign_id]=" + campaign_id + filters )) return self._pagination(url) |