Created
February 12, 2019 02:34
-
-
Save zhangtemplar/e74bded6ab48c9d766a5dfb372b7edc4 to your computer and use it in GitHub Desktop.
Change to scrapy_selenium to allow change proxy for each SeleniumRequest.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
"""This module contains the ``SeleniumMiddleware`` scrapy middleware""" | |
from importlib import import_module | |
from scrapy import signals | |
from scrapy.exceptions import NotConfigured | |
from scrapy.http import HtmlResponse | |
from selenium.webdriver.support.ui import WebDriverWait | |
from .http import SeleniumRequest | |
from proxy.pool import POOL | |
class SeleniumMiddleware: | |
"""Scrapy middleware handling the requests using selenium""" | |
def __init__(self, driver_name, driver_executable_path, driver_arguments, | |
browser_executable_path): | |
"""Initialize the selenium webdriver | |
Parameters | |
---------- | |
driver_name: str | |
The selenium ``WebDriver`` to use | |
driver_executable_path: str | |
The path of the executable binary of the driver | |
driver_arguments: list | |
A list of arguments to initialize the driver | |
browser_executable_path: str | |
The path of the executable binary of the browser | |
""" | |
webdriver_base_path = f'selenium.webdriver.{driver_name}' | |
driver_klass_module = import_module(f'{webdriver_base_path}.webdriver') | |
self.driver_klass = getattr(driver_klass_module, 'WebDriver') | |
driver_options_module = import_module(f'{webdriver_base_path}.options') | |
self.driver_options_klass = getattr(driver_options_module, 'Options') | |
self.driver_executable_path = driver_executable_path | |
self.driver_name = driver_name | |
self.browser_executable_path = browser_executable_path | |
self.driver_arguments = driver_arguments | |
self.drivers = [] | |
def _get_driver(self): | |
driver_options = self.driver_options_klass() | |
driver_options.add_argument("--proxy-server={}".format(POOL.get())) | |
if self.browser_executable_path: | |
driver_options.binary_location = self.browser_executable_path | |
for argument in self.driver_arguments: | |
driver_options.add_argument(argument) | |
driver_kwargs = { | |
'executable_path': self.driver_executable_path, | |
f'{self.driver_name}_options': driver_options | |
} | |
return self.driver_klass(**driver_kwargs) | |
@classmethod | |
def from_crawler(cls, crawler): | |
"""Initialize the middleware with the crawler settings""" | |
driver_name = crawler.settings.get('SELENIUM_DRIVER_NAME') | |
driver_executable_path = crawler.settings.get('SELENIUM_DRIVER_EXECUTABLE_PATH') | |
browser_executable_path = crawler.settings.get('SELENIUM_BROWSER_EXECUTABLE_PATH') | |
driver_arguments = crawler.settings.get('SELENIUM_DRIVER_ARGUMENTS') | |
if not driver_name or not driver_executable_path: | |
raise NotConfigured( | |
'SELENIUM_DRIVER_NAME and SELENIUM_DRIVER_EXECUTABLE_PATH must be set' | |
) | |
middleware = cls( | |
driver_name=driver_name, | |
driver_executable_path=driver_executable_path, | |
driver_arguments=driver_arguments, | |
browser_executable_path=browser_executable_path | |
) | |
crawler.signals.connect(middleware.spider_closed, signals.spider_closed) | |
return middleware | |
def process_request(self, request, spider): | |
"""Process a request using the selenium driver if applicable""" | |
if not isinstance(request, SeleniumRequest): | |
return None | |
driver = self._get_driver() | |
driver.get(request.url) | |
for cookie_name, cookie_value in request.cookies.items(): | |
driver.add_cookie( | |
{ | |
'name': cookie_name, | |
'value': cookie_value | |
} | |
) | |
if request.wait_until: | |
WebDriverWait(driver, request.wait_time).until( | |
request.wait_until | |
) | |
if request.screenshot: | |
request.meta['screenshot'] = driver.get_screenshot_as_png() | |
body = str.encode(driver.page_source) | |
# Expose the driver via the "meta" attribute | |
request.meta.update({'driver': driver}) | |
return HtmlResponse( | |
driver.current_url, | |
body=body, | |
encoding='utf-8', | |
request=request | |
) | |
def spider_closed(self): | |
"""Shutdown the driver when spider is closed""" | |
for driver in self.drivers: | |
try: | |
driver.quit() | |
finally: | |
pass | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment