first commit

Author: azhengyongqin

.github/workflows/publish.yml

@@ -0,0 +1,34 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [ created ]
+
+jobs:
+  pypi-publish:
+    name: Publish release to PyPI
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/scrapeless
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.x"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install setuptools wheel
+
+      - name: Build package
+        run: |
+          python setup.py sdist bdist_wheel  # Could also be python -m build
+
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

.gitignore

@@ -0,0 +1,10 @@
+*/**/__pycache__/*
+*/**/*.pyc
+*/**/*.pyo
+*/**/*.pyd
+*/**/*.pyw
+*/**/*.pyz
+*/**/*.pywz
+*/**/*.pyzw
+.vscode
+.idea

README.md

@@ -0,0 +1,63 @@
+# Scrapeless Python SDK
+
+## install
+```shell
+pip install scrapeless-sdk-python
+```
+
+## Usage
+
+Start using the API with your [API KEY](https://app.scrapeless.com/dashboard/account?tab=apiKey)
+
+For more examples, please refer to the `examples` directory
+
+For more information, please refer to our [documentation](https://docs.scrapeless.com/)
+
+### Scraping API
+```python
+from scrapeless import ScrapelessClient
+
+scrapeless = ScrapelessClient(api_key='your-api-key')
+
+actor = "scraper.shopee"
+input_data = {
+  "type": "shopee.product",
+  "url": "https://shopee.tw/2312312.10228173.24803858474"
+}
+
+result = scrapeless.scraper(actor, input=input_data)
+```
+
+### Web Unlocker
+```python
+from scrapeless import ScrapelessClient
+
+scrapeless = ScrapelessClient(api_key='your-api-key')
+
+actor = 'unlocker.webunlocker'
+input_data = {
+  "url": "https://www.scrapeless.com",
+  "proxy_country": "ANY",
+  "method": "GET",
+  "redirect": false,
+}
+
+result = scrapeless.unlocker(actor, input=input_data)
+```
+
+### Captcha Solver
+```python
+from scrapeless import ScrapelessClient
+
+scrapeless = ScrapelessClient(api_key='your-api-key')
+
+actor = 'captcha.recaptcha'
+input_data = {
+  "version": "v2",
+  "pageURL": "https://www.google.com",
+  "siteKey": "6Le-wvkSAAAAAPBMRTvw0Q4Muexq9bi0DJwx_mJ-",
+  "pageAction": ""
+}
+
+result = scrapeless.captcha(actor, input=input_data)
+```

examples/captcha/recaptcha-enterprise.py

@@ -0,0 +1,39 @@
+# if you want to run this example, you need to replace "your-api-key"
+# import sys
+# import os
+# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../../")))
+
+import time
+from scrapeless import ScrapelessClient
+
+scrapeless = ScrapelessClient(api_key="your-api-key")
+
+def solve_captcha():
+  actor = "captcha.recaptcha.enterprise"
+  input_data = {
+    "version": "v3",
+    "pageURL": "https://www.google.com",
+    "siteKey": "6Le-wvkSAAAAAPBMRTvw0Q4Muexq9bi0DJwx_mJ-",
+    "pageAction": "scraping",
+    "invisible": False
+  }
+
+  result = scrapeless.captcha(actor, input=input_data)
+  return result
+
+def get_captcha_result(taskId):
+  result = scrapeless.get_captcha_result(taskId)
+  return result
+
+def main():
+  captcha_result = solve_captcha()
+  taskId = captcha_result["taskId"]
+
+  while True:
+    captcha_result = get_captcha_result(taskId)
+    if captcha_result["success"] == True:
+      print(captcha_result)
+      break
+    time.sleep(5)
+
+main()

examples/captcha/recaptcha.py

@@ -0,0 +1,39 @@
+# you can run this example by executing `python examples/captcha/captcha.py` in the terminal
+# if you want to run this example, you need to replace "your-api-key"
+import sys
+import os
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../../")))
+
+import time
+from scrapeless import ScrapelessClient
+
+scrapeless = ScrapelessClient(api_key="your-api-key")
+
+def solve_captcha():
+  actor = "captcha.recaptcha"
+  input_data = {
+    "version": "v2",
+    "pageURL": "https://www.google.com",
+    "siteKey": "6Le-wvkSAAAAAPBMRTvw0Q4Muexq9bi0DJwx_mJ-",
+    "pageAction": ""
+  }
+
+  result = scrapeless.captcha(actor, input=input_data)
+  return result
+
+def get_captcha_result(taskId):
+  result = scrapeless.get_captcha_result(taskId)
+  return result
+
+def main():
+  captcha_result = solve_captcha()
+  taskId = captcha_result["taskId"]
+
+  while True:
+    captcha_result = get_captcha_result(taskId)
+    if captcha_result["success"]:
+      print(captcha_result)
+      break
+    time.sleep(5)
+
+main()

examples/scraper/br-consopt.py

@@ -0,0 +1,23 @@
+# if you want to run this example, you need to replace "your-api-key"
+# import sys
+# import os
+# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../../")))
+
+from scrapeless import ScrapelessClient
+
+scrapeless = ScrapelessClient(api_key="your-api-key")
+
+def br_consopt():
+  result = scrapeless.scraper(
+    actor="scraper.consopt",
+    input={
+      "taxId": "25032537000164",
+    },
+    proxy={
+      "country": "US",
+    }
+  )
+
+  print(result)
+
+br_consopt()

examples/scraper/br-solucoes.py

@@ -0,0 +1,23 @@
+# if you want to run this example, you need to replace "your-api-key"
+# import sys
+# import os
+# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../../")))
+
+from scrapeless import ScrapelessClient
+
+scrapeless = ScrapelessClient(api_key="your-api-key")
+
+def br_solucoes():
+  result = scrapeless.scraper(
+    actor="scraper.solucoes",
+    input={
+      "taxId": "37.335.118/0001-80",
+    },
+    proxy={
+      "country": "US",
+    }
+  )
+
+  print(result)
+
+br_solucoes()

examples/scraper/iberia.py

@@ -0,0 +1,26 @@
+# if you want to run this example, you need to replace "your-api-key"
+# import sys
+# import os
+# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../../")))
+
+from scrapeless import ScrapelessClient
+
+scrapeless = ScrapelessClient(api_key="your-api-key")
+
+def iberia():
+  result = scrapeless.scraper(
+    actor="scraper.iberia",
+    input={
+      "proxy": "72.46.64.6:65173:ssxiqsom:VA8ji024fz",
+      "username": "00000116280546",
+      "password": "i72sV7CWbDZ+7",
+      "body": "{\"slices\":[{\"origin\":\"NYC\",\"destination\":\"SHA\",\"date\":\"2024-11-03\"}],\"passengers\":[{\"passengerType\":\"ADULT\",\"count\":1}],\"marketCode\":\"US\",\"preferredCabin\":\"\"}"
+    },
+    proxy={
+      "country": "US",
+    }
+  )
+
+  print(result)
+
+iberia()

examples/scraper/shopee-live.py

@@ -0,0 +1,21 @@
+# if you want to run this example, you need to replace "your-api-key"
+# import sys
+# import os
+# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../../")))
+
+from scrapeless import ScrapelessClient
+
+scrapeless = ScrapelessClient(api_key="your-api-key")
+
+def shopee_live():
+  result = scrapeless.scraper(
+    actor="scraper.shopee",
+    input={
+      "type": "shopee.live",
+      "url": "https://live.shopee.co.th/api/v1/session/13285347",
+    }
+  )
+
+  print(result)
+
+shopee_live()

examples/unlocker/akamaiweb-cookie.py

@@ -0,0 +1,23 @@
+# if you want to run this example, you need to replace "your-api-key"
+# import sys
+# import os
+# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../../")))
+
+from scrapeless import ScrapelessClient
+
+scrapeless = ScrapelessClient(api_key="your-api-key")
+
+def web_unlocker():
+  result = scrapeless.scraper(
+    actor="unlocker.akamaiweb",
+    input={
+      "type": "cookie",
+      "proxy_country": "ANY",
+      "url": "https://www.iberia.com/",
+      "userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36",
+    }
+  )
+
+  print(result)
+
+web_unlocker()

examples/unlocker/akamaiweb-sensor.py

@@ -0,0 +1,23 @@
+# if you want to run this example, you need to replace "your-api-key"
+# import sys
+# import os
+# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../../")))
+
+from scrapeless import ScrapelessClient
+
+scrapeless = ScrapelessClient(api_key="your-api-key")
+
+def web_unlocker():
+  result = scrapeless.scraper(
+    actor="unlocker.akamaiweb",
+    input={
+      "abck": "xxxx",
+      "bmsz": "xxxx",
+      "url": "https://www.scrapeless.com",
+      "userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36"
+    }
+  )
+
+  print(result)
+
+web_unlocker()

examples/unlocker/webunlocker.py

@@ -0,0 +1,23 @@
+# if you want to run this example, you need to replace "your-api-key"
+# import sys
+# import os
+# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../../")))
+
+from scrapeless import ScrapelessClient
+
+scrapeless = ScrapelessClient(api_key="your-api-key")
+
+def web_unlocker():
+  result = scrapeless.scraper(
+    actor="unlocker.webunlocker",
+    input={
+      "url": "https://www.scrapeless.com",
+      "proxy_country": "ANY",
+      "method": "GET",
+      "redirect": False,
+    }
+  )
+
+  print(result)
+
+web_unlocker()

pyproject.toml

@@ -0,0 +1,3 @@
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"

scrapeless/__init__.py

@@ -0,0 +1,3 @@
+from scrapeless.client import ScrapelessClient
+
+__all__ = ["ScrapelessClient"]

scrapeless/__version__.py

@@ -0,0 +1 @@
+__version__ = '0.0.1'