![\"python\u5982\u4f55\u5199\u5206\u5e03\u5f0f\u722c\u866b\"](\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/964dbbce-147f-46a7-bcd5-6667aa5c760c.webp?x-oss-process=image\/auto-orient,1\/format,webp\")
<\/p>\n<\/p>\n
Python\u5199\u5206\u5e03\u5f0f\u722c\u866b\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528Scrapy-Redis\u3001\u4f7f\u7528Celery\u3001\u4f7f\u7528PySpark\u3001\u7ed3\u5408Docker\u5b9e\u73b0\u5bb9\u5668\u5316\u90e8\u7f72\u3002<\/strong>\u5176\u4e2d\uff0c\u4f7f\u7528Scrapy-Redis\u662f\u4e00\u79cd\u5e38\u89c1\u4e14\u9ad8\u6548\u7684\u89e3\u51b3\u65b9\u6848\u3002<\/p>\n<\/p>\n Scrapy-Redis\u662f\u4e00\u79cd\u975e\u5e38\u6d41\u884c\u7684\u5206\u5e03\u5f0f\u722c\u866b\u6846\u67b6\uff0c\u5b83\u57fa\u4e8eScrapy\u6846\u67b6\uff0c\u901a\u8fc7Redis\u6570\u636e\u5e93\u5b9e\u73b0\u4efb\u52a1\u961f\u5217\u548c\u6570\u636e\u5b58\u50a8\u7684\u5206\u5e03\u5f0f\u722c\u866b\u3002Scrapy-Redis\u7684\u4f18\u70b9\u5728\u4e8e\u5176\u9ad8\u6269\u5c55\u6027\u548c\u6613\u7528\u6027\uff0c\u53ef\u4ee5\u8f7b\u677e\u5730\u5c06\u722c\u866b\u4efb\u52a1\u5206\u53d1\u5230\u591a\u53f0\u673a\u5668\u4e0a\uff0c\u5e76\u4e14\u901a\u8fc7Redis\u6765\u5b9e\u73b0\u4efb\u52a1\u7684\u53bb\u91cd\u548c\u8c03\u5ea6\u3002<\/p>\n<\/p>\n \u4e00\u3001\u4f7f\u7528Scrapy-Redis\u5b9e\u73b0\u5206\u5e03\u5f0f\u722c\u866b<\/p>\n<\/p>\n \u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5Scrapy-Redis\u548cRedis\u3002\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5\uff1a<\/p>\n<\/p>\n <\/code><\/pre>\n<\/p>\n \u5b89\u88c5Redis\u670d\u52a1\u5668\uff0c\u53ef\u4ee5\u53c2\u8003Redis\u5b98\u65b9\u6587\u6863\u8fdb\u884c\u5b89\u88c5\u3002<\/p>\n<\/p>\n \u5728Scrapy\u9879\u76ee\u7684settings.py\u6587\u4ef6\u4e2d\uff0c\u6dfb\u52a0\u4ee5\u4e0b\u914d\u7f6e\uff1a<\/p>\n<\/p>\n SCHEDULER = "scrapy_redis.scheduler.Scheduler"<\/p>\n DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"<\/p>\n SCHEDULER_PERSIST = True<\/p>\n REDIS_HOST = 'localhost'<\/p>\n REDIS_PORT = 6379<\/p>\n <\/code><\/pre>\n<\/p>\n \u5c06Scrapy\u9879\u76ee\u4e2d\u7684Spider\u4fee\u6539\u4e3a\u7ee7\u627f\u81eascrapy_redis.spiders.RedisSpider\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n from scrapy_redis.spiders import RedisSpider<\/p>\n class MySpider(RedisSpider):<\/p>\n name = 'my_spider'<\/p>\n redis_key = 'my_spider:start_urls'<\/p>\n def parse(self, response):<\/p>\n # \u89e3\u6790\u903b\u8f91<\/p>\n pass<\/p>\n <\/code><\/pre>\n<\/p>\n \u9996\u5148\uff0c\u542f\u52a8Redis\u670d\u52a1\u5668\u3002\u7136\u540e\uff0c\u5728Redis\u4e2d\u6dfb\u52a0\u8d77\u59cbURL\uff1a<\/p>\n<\/p>\n <\/code><\/pre>\n<\/p>\n \u6700\u540e\uff0c\u542f\u52a8Scrapy\u722c\u866b\uff1a<\/p>\n<\/p>\n <\/code><\/pre>\n<\/p>\n \u4e8c\u3001\u4f7f\u7528Celery\u5b9e\u73b0\u5206\u5e03\u5f0f\u722c\u866b<\/p>\n<\/p>\n \u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5Celery\u548cRedis\uff1a<\/p>\n<\/p>\n <\/code><\/pre>\n<\/p>\n \u5728\u9879\u76ee\u6839\u76ee\u5f55\u4e0b\u521b\u5efacelery.py\u6587\u4ef6\uff0c\u6dfb\u52a0\u4ee5\u4e0b\u914d\u7f6e\uff1a<\/p>\n<\/p>\n app = Celery('tasks', broker='redis:\/\/localhost:6379\/0')<\/p>\n app.conf.update(<\/p>\n result_backend='redis:\/\/localhost:6379\/0',<\/p>\n task_serializer='json',<\/p>\n accept_content=['json'],<\/p>\n result_serializer='json',<\/p>\n timezone='UTC',<\/p>\n enable_utc=True,<\/p>\n )<\/p>\n <\/code><\/pre>\n<\/p>\n \u5728\u9879\u76ee\u6839\u76ee\u5f55\u4e0b\u521b\u5efatasks.py\u6587\u4ef6\uff0c\u5b9a\u4e49\u722c\u866b\u4efb\u52a1\uff1a<\/p>\n<\/p>\n import requests<\/p>\n @shared_task<\/p>\n def fetch_url(url):<\/p>\n response = requests.get(url)<\/p>\n return response.text<\/p>\n <\/code><\/pre>\n<\/p>\n \u542f\u52a8Celery worker\uff1a<\/p>\n<\/p>\n <\/code><\/pre>\n<\/p>\n \u5728\u9879\u76ee\u4e2d\u8c03\u7528fetch_url\u4efb\u52a1\uff1a<\/p>\n<\/p>\n urls = ['http:\/\/example.com', 'http:\/\/example.org']<\/p>\n for url in urls:<\/p>\n fetch_url.delay(url)<\/p>\n <\/code><\/pre>\n<\/p>\n \u4e09\u3001\u4f7f\u7528PySpark\u5b9e\u73b0\u5206\u5e03\u5f0f\u722c\u866b<\/p>\n<\/p>\n \u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5PySpark\uff1a<\/p>\n<\/p>\n <\/code><\/pre>\n<\/p>\n \u5728\u9879\u76ee\u4e2d\u914d\u7f6eSparkContext\u548cSparkSession\uff1a<\/p>\n<\/p>\n from pyspark.sql import SparkSession<\/p>\n conf = SparkConf().setAppName('DistributedCrawler').setMaster('local[*]')<\/p>\n sc = SparkContext(conf=conf)<\/p>\n spark = SparkSession.builder.config(conf=conf).getOrCreate()<\/p>\n <\/code><\/pre>\n<\/p>\n \u4f7f\u7528map\u51fd\u6570\u5e76\u884c\u6267\u884c\u722c\u866b\u4efb\u52a1\uff1a<\/p>\n<\/p>\n def fetch_url(url):<\/p>\n response = requests.get(url)<\/p>\n return response.text<\/p>\n urls = ['http:\/\/example.com', 'http:\/\/example.org']<\/p>\n rdd = sc.parallelize(urls)<\/p>\n results = rdd.map(fetch_url).collect()<\/p>\n for result in results:<\/p>\n print(result)<\/p>\n <\/code><\/pre>\n<\/p>\n \u56db\u3001\u7ed3\u5408Docker\u5b9e\u73b0\u5bb9\u5668\u5316\u90e8\u7f72<\/p>\n<\/p>\n \u5728\u9879\u76ee\u6839\u76ee\u5f55\u4e0b\u521b\u5efaDockerfile\uff0c\u5b9a\u4e49\u955c\u50cf\u6784\u5efa\u8fc7\u7a0b\uff1a<\/p>\n<\/p>\n WORKDIR \/app<\/p>\n COPY . \/app<\/p>\n RUN pip install -r requirements.txt<\/p>\n CMD ["scrapy", "crawl", "my_spider"]<\/p>\n <\/code><\/pre>\n<\/p>\n \u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u6784\u5efaDocker\u955c\u50cf\uff1a<\/p>\n<\/p>\n <\/code><\/pre>\n<\/p>\n \u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fd0\u884cDocker\u5bb9\u5668\uff1a<\/p>\n<\/p>\n <\/code><\/pre>\n<\/p>\n \u901a\u8fc7\u4ee5\u4e0a\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Scrapy-Redis\u3001Celery\u3001PySpark\u548cDocker\u5206\u522b\u5b9e\u73b0\u5206\u5e03\u5f0f\u722c\u866b\u3002\u6bcf\u79cd\u65b9\u6cd5\u90fd\u6709\u5176\u4f18\u70b9\u548c\u9002\u7528\u573a\u666f\uff0c\u53ef\u4ee5\u6839\u636e\u5b9e\u9645\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6848\u3002Scrapy-Redis\u9002\u7528\u4e8e\u9700\u8981\u9ad8\u6548\u8c03\u5ea6\u548c\u53bb\u91cd\u7684\u573a\u666f\uff0cCelery\u9002\u7528\u4e8e\u4efb\u52a1\u961f\u5217\u548c\u5f02\u6b65\u5904\u7406\uff0cPySpark\u9002\u7528\u4e8e\u5927\u89c4\u6a21\u6570\u636e\u5904\u7406\u548c\u8ba1\u7b97\uff0cDocker\u5219\u9002\u7528\u4e8e\u5bb9\u5668\u5316\u90e8\u7f72\u548c\u9694\u79bb\u73af\u5883\u3002<\/strong><\/p>\n<\/p>\n \u5982\u4f55\u9009\u62e9\u5408\u9002\u7684\u5206\u5e03\u5f0f\u722c\u866b\u6846\u67b6\uff1f<\/strong> \u5982\u4f55\u5904\u7406\u5206\u5e03\u5f0f\u722c\u866b\u4e2d\u7684\u6570\u636e\u5b58\u50a8\u95ee\u9898\uff1f<\/strong> \u5206\u5e03\u5f0f\u722c\u866b\u7684\u9519\u8bef\u5904\u7406\u548c\u91cd\u8bd5\u673a\u5236\u5e94\u8be5\u5982\u4f55\u8bbe\u8ba1\uff1f<\/strong>\n
pip install scrapy-redis<\/p>\n\n
# \u4f7f\u7528Scrapy-Redis\u7684\u8c03\u5ea6\u5668<\/p>\n\u4f7f\u7528Scrapy-Redis\u7684\u53bb\u91cd\u7c7b<\/strong><\/h2>\n
\u542f\u7528\u6301\u4e45\u5316<\/strong><\/h2>\n
Redis\u6570\u636e\u5e93\u8fde\u63a5\u914d\u7f6e<\/strong><\/h2>\n
\n
import scrapy<\/p>\n\n
redis-cli lpush my_spider:start_urls http:\/\/example.com<\/p>\nscrapy crawl my_spider<\/p>\n\n
pip install celery[redis]<\/p>\n\n
from celery import Celery<\/p>\n\n
from celery import shared_task<\/p>\n\n
celery -A tasks worker --loglevel=info<\/p>\n\n
from tasks import fetch_url<\/p>\n\n
pip install pyspark<\/p>\n\n
from pyspark import SparkContext, SparkConf<\/p>\n\n
import requests<\/p>\n\n
FROM python:3.8-slim<\/p>\n\n
docker build -t distributed-crawler .<\/p>\n\n
docker run -d distributed-crawler<\/p>\n\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
\u5728\u9009\u62e9\u5206\u5e03\u5f0f\u722c\u866b\u6846\u67b6\u65f6\uff0c\u53ef\u4ee5\u8003\u8651\u51e0\u4e2a\u5173\u952e\u56e0\u7d20\uff0c\u5305\u62ec\u6846\u67b6\u7684\u6613\u7528\u6027\u3001\u793e\u533a\u652f\u6301\u3001\u6587\u6863\u5b8c\u6574\u6027\u4ee5\u53ca\u6269\u5c55\u6027\u3002\u5e38\u89c1\u7684\u6846\u67b6\u5982Scrapy\u3001Scrapy-Redis\u548cPySpider\u7b49\uff0c\u90fd\u662f\u70ed\u95e8\u7684\u9009\u62e9\u3002Scrapy\u4ee5\u5176\u5f3a\u5927\u7684\u529f\u80fd\u548c\u4e30\u5bcc\u7684\u63d2\u4ef6\u751f\u6001\u53d7\u5230\u5e7f\u6cdb\u6b22\u8fce\uff0c\u800cScrapy-Redis\u5219\u901a\u8fc7Redis\u5b9e\u73b0\u4e86\u5206\u5e03\u5f0f\u7279\u6027\uff0c\u9002\u5408\u9700\u8981\u9ad8\u6548\u8d44\u6e90\u7ba1\u7406<\/a>\u7684\u9879\u76ee\u3002\u8bc4\u4f30\u8fd9\u4e9b\u6846\u67b6\u7684\u7279\u6027\uff0c\u53ef\u4ee5\u5e2e\u52a9\u4f60\u627e\u5230\u6700\u9002\u5408\u81ea\u5df1\u9700\u6c42\u7684\u5de5\u5177\u3002<\/p>\n
\u5728\u5206\u5e03\u5f0f\u722c\u866b\u4e2d\uff0c\u6570\u636e\u5b58\u50a8\u662f\u4e00\u4e2a\u91cd\u8981\u7684\u95ee\u9898\uff0c\u901a\u5e38\u9700\u8981\u9009\u62e9\u4e00\u4e2a\u9ad8\u6548\u4e14\u53ef\u6269\u5c55\u7684\u6570\u636e\u5e93\u3002\u5e38\u89c1\u7684\u9009\u62e9\u5305\u62ecMongoDB\u3001MySQL\u548cElasticsearch\u7b49\u3002MongoDB\u9002\u5408\u5b58\u50a8\u5927\u89c4\u6a21\u7684\u975e\u7ed3\u6784\u5316\u6570\u636e\uff0cMySQL\u5219\u9002\u5408\u7ed3\u6784\u5316\u6570\u636e\u7684\u5b58\u50a8\uff0c\u800cElasticsearch\u5219\u5728\u5168\u6587\u641c\u7d22\u548c\u5feb\u901f\u67e5\u8be2\u65b9\u9762\u8868\u73b0\u51fa\u8272\u3002\u6b64\u5916\uff0c\u4f7f\u7528\u6d88\u606f\u961f\u5217\uff08\u5982Kafka\uff09\u6765\u5904\u7406\u4efb\u52a1\u548c\u6570\u636e\u6d41\u8f6c\uff0c\u4e5f\u80fd\u63d0\u9ad8\u6570\u636e\u5904\u7406\u7684\u6548\u7387\u3002<\/p>\n
\u5728\u5206\u5e03\u5f0f\u722c\u866b\u4e2d\uff0c\u9519\u8bef\u5904\u7406\u548c\u91cd\u8bd5\u673a\u5236\u662f\u786e\u4fdd\u6570\u636e\u5b8c\u6574\u6027\u548c\u6293\u53d6\u6210\u529f\u7387\u7684\u5173\u952e\u3002\u5e94\u5b9e\u73b0\u4e00\u4e2a\u7075\u6d3b\u7684\u91cd\u8bd5\u7b56\u7565\uff0c\u4f8b\u5982\u5728\u9047\u5230\u7f51\u7edc\u9519\u8bef\u3001\u670d\u52a1\u5668\u9519\u8bef\u6216\u8d85\u65f6\u7b49\u60c5\u51b5\u4e0b\uff0c\u8bbe\u7f6e\u5408\u7406\u7684\u91cd\u8bd5\u6b21\u6570\u548c\u95f4\u9694\u3002\u540c\u65f6\uff0c\u53ef\u4ee5\u8bb0\u5f55\u5931\u8d25\u7684\u8bf7\u6c42\uff0c\u5e76\u5c06\u5176\u5b58\u5165\u4e00\u4e2a\u5f85\u5904\u7406\u961f\u5217\uff0c\u4ee5\u4fbf\u540e\u7eed\u91cd\u65b0\u6293\u53d6\u3002\u6b64\u5916\uff0c\u4f7f\u7528\u65e5\u5fd7\u7cfb\u7edf\u6765\u8bb0\u5f55\u6293\u53d6\u8fc7\u7a0b\u4e2d\u7684\u9519\u8bef\u4fe1\u606f\uff0c\u4e5f\u80fd\u5e2e\u52a9\u540e\u671f\u7684\u8c03\u8bd5\u4e0e\u4f18\u5316\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u5199\u5206\u5e03\u5f0f\u722c\u866b\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528Scrapy-Redis\u3001\u4f7f\u7528Celery\u3001\u4f7f\u7528PySpark\u3001\u7ed3\u5408D […]","protected":false},"author":3,"featured_media":1027623,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1027610"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1027610"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1027610\/revisions"}],"predecessor-version":[{"id":1027625,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1027610\/revisions\/1027625"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1027623"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1027610"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1027610"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1027610"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}