python-3.x - Webkit_server(从 python 的 dryscrape 调用)在访问每个页面时使用越来越多的内存。如何减少使用的内存？

Question

我正在 python3 中使用 dryscrape 编写一个scraper。我试图在 __scraping __session 期间访问数百个不同的 url，并在每个 url 上单击大约 10 个 ajax 页面(不访问每个 ajax 页面的不同 url)。我需要像 dryscrape 这样的东西，因为我需要能够与 javascript 组件交互。我为自己的需要编写的类可以工作，但是当我访问大约 50 或 100 页时，我的内存就用完了(所有 4Gbs 的内存都被使用了，4Gbs 的交换磁盘空间几乎 100% 满了)。我查看了内存占用情况，似乎是 webkit_server 进程负责所有内存。为什么会发生这种情况，我该如何避免？

下面是我的类和我的主要方法的相关片段。

这是使用 dryscape 的类，您可以准确地看到我正在使用的设置。

import dryscrape
from lxml import html
from time import sleep
from webkit_server import InvalidResponseError
import re

from utils import unugly, my_strip, cleanhtml, stringify_children
from Profile import Profile, Question

class ExampleSession():
    
    def __init__(self, settings):
        self.settings = settings
        # dryscrape.start_xvfb()
        self.br = self.getBrowser()

    def getBrowser(self):
        session = dryscrape.Session()
        session.set_attribute('auto_load_images', False)
        session.set_header('User-agent', 'Google Chrome')
        return session
        
    def login(self):
        try:
            print('Trying to log in... ')
            self.br.visit('https://www.example.com/login')                        
            self.br.at_xpath('//*[@id="login_username"]').set(self.settings['myUsername'])
            self.br.at_xpath('//*[@id="login_password"]').set(self.settings['myPassword'])
            q = self.br.at_xpath('//*[@id="loginbox_form"]')
            q.submit()
        except Exception as e:
            print(str(e))
            print('\tException and couldn\'t log in!')
            return
        print('Logged in as %s' % (str(self.settings['myUsername']))) 
                
    def getProfileQuestionsByUrl(self, url, thread_id=0):
        self.br.visit(str(url.rstrip()) + '/questions')
        
        tree = html.fromstring(self.br.body())
        questions = []
        
        num_pages = int(my_strip(tree.xpath('//*[@id="questions_pages"]//*[@class="last"]')[0].text))
    
        page = 0
        while (page < num_pages):
            sleep(0.5)
            # Do something with each ajax page
            # Next try-except tries to click the 'next' button
            try:
                next_button = self.br.at_xpath('//*[@id="questions_pages"]//*[@class="next"]')
                next_button.click()
            except Exception as e:
                pass                
            page = page + 1

        return questions
    
    def getProfileByUrl(self, url, thread_id=0):
        missing = 'NA'

        try:
            try:
                # Visit a unique url
                self.br.visit(url.rstrip())
            except Exception as e:
                print(str(e))
                return None
            tree = html.fromstring(self.br.body())

            map = {}
            # Fill up the dictionary with some things I find on the page
            
            profile = Profile(map)    
            return profile
        except Exception as e:
            print(str(e))
            return None

这是主要方法(片段):

def getProfiles(settings, urls, thread_id):
    exampleSess = ExampleSession(settings)
    exampleSess.login()

    profiles = []
    '''
    I want to visit at most a thousand unique urls (but I don't care if it
    will take 2 hours or 2 days as long as the session doesn't fatally break
    and my laptop doesn't run out of memory)
    '''
    for url in urls:            
        try:
            profile = exampleSess.getProfileByUrl(url, thread_id)
    
            if (profile is not None):
                profiles.append(profile)
                
                try:
                    if (settings['scrapeQuestions'] == 'yes'):
                        profile_questions = exampleSess.getProfileQuestionsByUrl(url, thread_id)
                    
                        if (profile_questions is not None):
                            profile.add_questions(profile_questions)
                except SocketError as e:
                    print(str(e))
                    print('\t[Thread %d] SocketError in getProfileQuestionsByUrl of profile...' % (thread_id))
                        
        except Exception as e:
            print(str(e))
            print('\t[Thread %d] Exception while getting profile %s' % (thread_id, str(url.rstrip())))
            okc.br.reset()
    
    exampleSession = None # Does this kill my dryscrape session and prevents webkit_server from running? 
    
    return profiles

我是否正确设置了dryscrape？ dryscrape 的 webkit_server 如何在我使用 getProfileByUrl 和 getProfileQuestionsByUrl？是否有任何我遗漏的设置可能会增加内存使用量？

Answer 1

我无法解决内存问题(我可以在另一台笔记本电脑上重现此问题)。我最终从 dryscrape 切换到 selenium(然后切换到 phantomjs)。 PhantomJS 在我看来更胜一筹，而且它也没有占用大量内存。