From 4674d5599e71d4582819800bdcb695ece29fb6bf Mon Sep 17 00:00:00 2001
From: Tweeticoats <60335703+Tweeticoats@users.noreply.github.com>
Date: Sun, 4 Jul 2021 16:31:18 +0930
Subject: [PATCH] Adding multiscrape python based performer scraper. (#594)

---
 scrapers/multiscrape.py  | 253 +++++++++++++++++++++++++++++++++++++++
 scrapers/multiscrape.yml |  17 +++
 2 files changed, 270 insertions(+)
 create mode 100644 scrapers/multiscrape.py
 create mode 100644 scrapers/multiscrape.yml

diff --git a/scrapers/multiscrape.py b/scrapers/multiscrape.py
new file mode 100644
index 000000000..e0ea2afc3
--- /dev/null
+++ b/scrapers/multiscrape.py
@@ -0,0 +1,253 @@
+
+import json
+import requests
+import sys
+
+
+class multiscrape:
+
+    url="http://localhost:9999/graphql"
+    headers = {
+        "Accept-Encoding": "gzip, deflate, br",
+        "Content-Type": "application/json",
+        "Accept": "application/json",
+        "Connection": "keep-alive",
+        "DNT": "1"
+    }
+
+    '''
+    update the below config in the preferred order for each field.
+    If there are no results for that performer and field it will use the results of the next scraper in the list and cache the results.'''
+    config ={
+        "gender": ['stash-sqlite'],
+        "url" : ['Babepedia','stash-sqlite','FreeonesCommunity','Brazzers','Pornhub'],
+        "twitter":['Babepedia','stash-sqlite'],
+        "instagram": ['Babepedia'],
+        "birthdate": ['IMBD','FreeonesCommunity','Babepedia','stash-sqlite'],
+         "ethnicity":  ['Babepedia','stash-sqlite'],
+         "country": ['Babepedia','stash-sqlite'],
+         "eye_color": ['Babepedia','stash-sqlite'],
+         "height":['Babepedia','Pornhub','stash-sqlite'],
+         "measurements":['Babepedia','Pornhub','FreeonesCommunity','stash-sqlite'],
+        "fake_tits":['Babepedia','stash-sqlite'],
+        "career_length": ['Pornhub','Babepedia','stash-sqlite'],
+        "tattoos":['Babepedia','stash-sqlite'],
+        "piercings": ['Babepedia','stash-sqlite'],
+        "aliases": ['Babepedia','stash-sqlite'],
+        "tags": ['Babepedia'],
+        "details": ['FreeonesCommunity','Babepedia','Brazzers'],
+        "death_date": ['Babepedia'],
+        "hair_color": ['Babepedia'],
+        "weight":['Babepedia','FreeonesCommunity'],
+        "image": ['performer-image-dir','Babepedia','FreeonesCommunity']
+    }
+
+
+    def __log(self,levelChar, s):
+        if levelChar == "":
+            return
+
+        print(self.__prefix(levelChar) + s + "\n", file=sys.stderr, flush=True)
+
+    def trace(self,s):
+        self.__log(b't', s)
+
+    def debug(self,s):
+        self.__log(b'd', s)
+
+    def info(self,s):
+        self.__log(b'i', s)
+
+    def warning(self,s):
+        self.__log(b'w', s)
+
+    def error(self,s):
+        self.__log(b'e', s)
+
+
+
+    def __callGraphQL(self, query, variables=None):
+        json = {}
+        json['query'] = query
+        if variables != None:
+            json['variables'] = variables
+
+        # handle cookies
+        response = requests.post(self.url, json=json, headers=self.headers)
+
+        if response.status_code == 200:
+            result = response.json()
+            if result.get("error", None):
+                for error in result["error"]["errors"]:
+                    raise Exception("GraphQL error: {}".format(error))
+            if result.get("data", None):
+                return result.get("data")
+        else:
+            raise Exception(
+                "GraphQL query failed:{} - {}. Query: {}. Variables: {}".format(response.status_code, response.content, query, variables))
+
+
+    def list_scrapers(self, type):
+        query = """query listPerformerScrapers {
+      listPerformerScrapers {
+        id
+        name
+        performer{
+          supported_scrapes
+        }
+      }
+    }"""
+        ret = []
+        result = self.__callGraphQL(query)
+        for r in result["listSceneScrapers"]:
+            if type in r["scene"]["supported_scrapes"]:
+                ret.append(r["id"])
+        return ret
+
+    def scrape_performer_list(self, scraper_id, performer):
+        query = """query scrapePerformerList($scraper_id: ID!, $performer: String!) {
+      scrapePerformerList(scraper_id: $scraper_id, query: $performer) {
+        name
+        url
+        gender
+        twitter
+        instagram
+        birthdate
+        ethnicity
+        country
+        eye_color
+        height
+        measurements
+        fake_tits
+        career_length
+        tattoos
+        piercings
+        aliases
+        image
+        }
+    }"""
+
+        variables = {'scraper_id': scraper_id, 'performer': performer}
+        result = self.__callGraphQL(query, variables)
+        if result is not None:
+            return result["scrapePerformerList"]
+        return None
+
+    def scrape_performer(self, scraper_id, performer):
+        query = """query scrapePerformer($scraper_id: ID!, $performer: ScrapedPerformerInput!) {
+  scrapePerformer(scraper_id: $scraper_id, scraped_performer: $performer) {
+    name
+    url
+    gender
+    twitter
+    instagram
+    birthdate
+    ethnicity
+    country
+    eye_color
+    height
+    measurements
+    fake_tits
+    career_length
+    tattoos
+    piercings
+    aliases
+    image
+    }
+}"""
+        variables = {'scraper_id': scraper_id, 'performer': performer}
+        result = self.__callGraphQL(query, variables)
+        return result["scrapePerformer"]
+
+    def requred_scrapers(self):
+        scrapers=[]
+        for key in self.config.keys():
+            for s in self.config.get(key):
+                if s not in scrapers:
+                    scrapers.append(s)
+        return scrapers
+
+
+    def query_performers(self,name):
+        ret=[]
+
+        for scraper in self.requred_scrapers():
+            print("Querying performers "+ scraper, file=sys.stderr)
+            tmp=self.scrape_performer_list(scraper,name)
+            if tmp is not None:
+                for s in tmp:
+                    found=False
+                    for t in ret:
+                        if s["name"]==t["name"]:
+                            found=True
+                    if not found:
+                        ret.append(s)
+        return ret
+
+    def fetch_performer(self,name):
+        ret={"name":name}
+
+        scraper_cache={}
+
+        for field in self.config.keys():
+            found=False
+            for s in self.config[field]:
+                if s in scraper_cache.keys():
+                    if field in scraper_cache[s]:
+                        ret[field]=scraper_cache[s][field]
+                        print("updating field from cache using scraper: " + s +" for field: " +field, file=sys.stderr)
+                        found=True
+                if s not in scraper_cache.keys() and not found:
+                    print("Running scraper: " + s +" " +field, file=sys.stderr)
+                    spl=self.scrape_performer_list(s, name)
+                    if spl is not None:
+                        for spli in spl:
+                            if spli["name"].lower()==name.lower():
+                                r=self.scrape_performer(s, {"name":spli["name"]})
+                                if r is not None:
+                                    scraper_cache[s]=r
+                                    found=True
+                                    break;
+                    if found:
+                        print("Saving results from scraper: " +field + " " +s,file=sys.stderr)
+                        if field in scraper_cache[s]:
+                            ret[field]=scraper_cache[s][field]
+                        else:
+                            found=False
+                    else:
+                        scraper_cache[s]={}
+        return ret
+
+
+
+if sys.argv[1] == "query":
+    fragment = json.loads(sys.stdin.read())
+    print("input: " + json.dumps(fragment),file=sys.stderr)
+    scraper=multiscrape()
+    result = scraper.query_performers(fragment['name'])
+    if not result:
+        print(f"Could not determine details for performer: `{fragment['name']}`",file=sys.stderr)
+        print("{}")
+    else:
+        print (json.dumps(result))
+
+if sys.argv[1] == "fetch":
+    fragment = json.loads(sys.stdin.read())
+    print("input: " + json.dumps(fragment),file=sys.stderr)
+    scraper=multiscrape()
+    result = scraper.fetch_performer(fragment['name'])
+    if not result:
+        print(f"Could not determine details for performer: `{fragment['name']}`",file=sys.stderr)
+        print("{}")
+    else:
+        True
+        print (json.dumps(result))
+
+
+
+if sys.argv[1] == "test":
+    scraper=multiscrape()
+    scrapers=scraper.requred_scrapers()
+    print(scrapers)
+
+
diff --git a/scrapers/multiscrape.yml b/scrapers/multiscrape.yml
new file mode 100644
index 000000000..6d7307340
--- /dev/null
+++ b/scrapers/multiscrape.yml
@@ -0,0 +1,17 @@
+name: multiscrape
+
+performerByFragment:
+    action: script
+    script:
+      - python
+      - multiscrape.py
+      - fetch
+
+performerByName:
+    action: script
+    script:
+      - python
+      - multiscrape.py
+      - query
+
+# Last Updated June 9, 2021