这让我发疯了。它驱使我整合和简化大量代码,但我无法解决问题。这是我写的两只蜘蛛的例子。顶部有一个内存泄漏,导致内存缓慢扩展直到满。
它们几乎是相同的,它们使用相同的项目和蜘蛛之外的其他所有内容,所以我认为我的其余代码中没有任何责任。我还在这里和那里隔离了一些代码,尝试在最后删除变量。我已经查看了刮擦的文档,但我仍然感到困惑。有人有魔法吗?
import scrapy
from wordscrape.items import WordScrapeItem
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
import json
class EnglishWikiSpider(CrawlSpider):
name='englishwiki'
allowed_domains = ['en.wikipedia.org']
start_urls = [
'http://en.wikipedia.org/wiki/'
]
rules = (
Rule(SgmlLinkExtractor(allow=('/wiki/', )), callback='parse_it', follow=True),
)
def parse_it(self, response):
the_item = WordScrapeItem()
# This takes all the text that is in that div and extracts it, only the text, not html tags (see: //text())
# if it meets the conditions of my regex
english_text = response.xpath('//*[@id="mw-content-text"]//text()').re(ur'[a-zA-Z'-]+')
english_dict = {}
for i in english_text:
if len(i) > 1:
word = i.lower()
if word in english_dict:
english_dict[word] += 1
else:
english_dict[word] = 1
# Dump into json string and put it in the word item, it will be ['word': {<<jsondict>>}, 'site' : url, ...]
jsondump = json.dumps(english_dict)
the_item['word'] = jsondump
the_item['site'] = response.url
return the_item
第二种,也是稳定的蜘蛛:
import scrapy
from wordscrape.items import WordScrapeItem
import re
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
import json
class NaverNewsSpider(CrawlSpider):
name='navernews'
allowed_domains = ['news.naver.com']
start_urls = [
'http://news.naver.com',
'http://news.naver.com/main/read.nhn?oid=001&sid1=102&aid=0007354749&mid=shm&cid=428288&mode=LSD&nh=20150114125510',
]
rules = (
Rule(SgmlLinkExtractor(allow=('main/read.nhn', )), callback='parse_it', follow=True),
)
def parse_it(self, response):
the_item = WordScrapeItem()
# gets all the text from the listed div and then applies the regex to find all word objects in hanul range
hangul_syllables = response.xpath('//*[@id="articleBodyContents"]//text()').re(ur'[uac00-ud7af]+')
# Go through all hangul syllables found and adds to value or adds key
hangul_dict = {}
for i in hangul_syllables:
if i in hangul_dict:
hangul_dict[i] += 1
else:
hangul_dict[i] = 1
jsondump = json.dumps(hangul_dict)
the_item['word'] = jsondump
the_item['site'] = response.url
return the_item
我认为杰皮奥的评论是正确的。我认为 spidder 找到了太多要遵循的链接,因此必须将它们全部存储在临时 perdiod 中。
编辑:所以,问题是它将所有这些链接存储在内存中而不是磁盘上,最终填满了我所有的内存。解决方案是使用作业目录运行,这迫使它们存储在有足够的空间的磁盘上。
$ 刮擦爬行蜘蛛 -s JOBDIR=somedirname