StellarTemp/CrawlerManager.py at master · CodeMallow/StellarTemp · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
# -*- coding: utf-8 -*-
"""
Created on Tue Mar  3 18:20:57 2020

@author: jindou
"""
import subprocess
from StellarLog.StellarLog import CLog
from diskcache import Cache

class CUrlList:

    def __init__(self,index,logInfo:dict):
        self.index  = index
        self.logInfo:dict = logInfo
        self.preInfoList:list = list()
        self._list:list = list()

    def append(self,url:str,preInfo:list):
        self._list.append(url)
        self.preInfoList.append(preInfo)

    def replace(self,List:list,preInfoList:list):
        if(type(preInfoList[0])!=list):
            raise ValueError('preInfoList must be list of list')
        self._list = List
        self.preInfoList = preInfoList

    def clear(self):
        self._list.clear()
        self.preInfoList.clear()

    def exportJson(self):
        import json
        jsonDict = {'index':self.index,
                    'logInfo':self.logInfo,
                    'preInfo':self.preInfoList,
                    'urlList':self._list}
        jsonStr = json.dumps(jsonDict)
        return jsonStr

    def __getitem__(self,idx):
        tempDict = self.logInfo.copy()
        tempDict['type'] = 'subList'
        oUrlList = CUrlList(self.index,tempDict)
        oUrlList._list = self._list[idx]
        oUrlList.preInfoList = self.preInfoList[idx]
        return oUrlList

    def __len__(self):
        return len(self._list)


class CCrawlerManager:
    def __init__(self,name,workDirectory:str, oLog:CLog,cachePath:str, cacheAgentPath:str):
        self.workDirectory = workDirectory
        self.jobsList = None
        self.oLog = oLog
        self.outputFolder = workDirectory
        self.name = name + '_crawler'
        self.jobCnt = 0
        self._cachePathCrawler = cachePath
        self._cachePathAgent = cacheAgentPath
        self.cache = Cache(cachePath)

    def _newProcess(self,crawlerName,oUrlCacheKey:str):
        outFilePath = 'file:///' + self.outputFolder + self.name + '.json'
#        print(outFilePath,urlsFilePath)
#        process = subprocess.Popen(['scrapy','crawl',crawlerName,'-o',outFilePath,'-a',
#                                    'cacheCrawlerPath='+ self._cachePathCrawler,'-a',
#                                    'cacheKey='+oUrlCacheKey,'-a',
#                                    'cacheAgentPath=' + self._cachePathAgent],
#                                   shell=True,
#                                   cwd=self.workDirectory)
#        print('scrapy','crawl',crawlerName,'-o',outFilePath,'-a',
#                                    'cacheCrawlerPath='+ self._cachePathCrawler,'-a',
#                                    'cacheKey='+oUrlCacheKey,'-a',
#                                    'cacheAgentPath=' + self._cachePathAgent)
        process = subprocess.Popen(['scrapy','crawl',crawlerName,'-a',
                                    'cacheCrawlerPath='+ self._cachePathCrawler,'-a',
                                    'cacheKey='+oUrlCacheKey,'-a',
                                    'cacheAgentPath=' + self._cachePathAgent],
                                   shell=True,
                                   cwd=self.workDirectory)
#        print('scrapy','crawl',crawlerName,'-a',
#                                    'cacheCrawlerPath='+ self._cachePathCrawler,'-a',
#                                    'cacheKey='+oUrlCacheKey,'-a',
#                                    'cacheAgentPath=' + self._cachePathAgent)

        return process

    def engineStart(self,jobsList:list):
        for oUrlList in jobsList:
            oUrlList.index = self.jobCnt
            tempKey = self._prepareJob(oUrlList.exportJson())
            self.oLog.safeRecordTime(str(oUrlList.index)+"start")
            temp = self._newProcess('general',tempKey)
#            temp.wait()
            self.oLog.safeRecordTime(str(oUrlList.index)+"end")
            return temp

    def _prepareJob(self,content:str):
#        key = str(self.jobCnt)
#        if(self.cache.get(key)==False):
#            raise ValueError("this key exists in the cache")
#            return None
#        else:
#            self.cache[key] = content
#            self.jobCnt+=1
#            return key
        self.jobCnt+=1
#        print(self.cache.directory)
        key = self.cache.push(content)
        return str(key)

    def closeCache(self):
        self.cache.close()

class CContentExtract():

    def __init__(self,mode='boilerpipe'):
        if(mode=='boilerpipe'):
            self.Module = self._importBoilerpipe3Extractor()
        else:
            raise ValueError("doesn't have this kind of mode")

    def boilerpipe(self,htmlText):

        extractor = self.Module(extractor='ArticleExtractor', html=htmlText)
        title = extractor.getTitle()
        content = extractor.getText()
        return title,content

    def _importBoilerpipe3Extractor(self):
        from boilerpipe.extract import Extractor
        return Extractor