Definition at line 31 of file EventObjects.py.
◆ __init__()
def dc.EventObjects.Site.__init__ |
( |
|
self, |
|
|
|
url, |
|
|
|
_userId = 0 |
|
) |
| |
Definition at line 58 of file EventObjects.py.
61 url = URL(siteId=0, url=url,
62 normalizeMask=UrlNormalizator.NORM_NONE).getURL(normalizeMask=UrlNormalizator.NORM_NONE)
65 self.id = hashlib.md5(url).hexdigest()
68 self.cDate = SQLExpression(
"NOW()")
74 self.state = self.STATE_ACTIVE
77 self.priority = self.DEFAULT_PRIORITY
85 self.maxResourceSize = 0
87 self.requestDelay = 500
89 self.processingDelay = 500
91 self.httpTimeout = 30000
101 self.avgSpeedCounter = 0
109 self.description =
"" 113 if url
is not None and len(url) > 0:
114 localUrl = SiteURL(siteId=self.id, url=url, normalizeMask=UrlNormalizator.NORM_NONE)
115 self.urls.append(localUrl)
118 self.filters = [SiteFilter(self.id,
"(.*)")]
121 self.properties = [{
"name":
"PROCESS_CTYPES",
"value":
"text/html"},
122 {
"name":
"STORE_HTTP_REQUEST",
"value":
"1"},
123 {
"name":
"STORE_HTTP_HEADERS",
"value":
"1"},
124 {
"name":
"HTTP_HEADERS",
"value":
""},
125 {
"name":
"HTTP_COOKIE",
"value":
""}]
126 self.userId = _userId
128 self.recrawlPeriod = 0
130 self.recrawlDate =
None 132 self.maxURLsFromPage = 0
134 self.collectedURLs = 0
136 self.fetchType = self.FETCH_TYPE_STATIC
143 self.tcDateProcess =
None 144 self.categoryId = self.DEFAULT_CATEGORY_ID
def __init__(self)
constructor
◆ getFromProperties()
def dc.EventObjects.Site.getFromProperties |
( |
|
prop, |
|
|
|
keyName, |
|
|
|
fieldName = "value" |
|
) |
| |
|
static |
Definition at line 193 of file EventObjects.py.
193 def getFromProperties(prop, keyName, fieldName="value"):
196 if isinstance(prop, dict)
and keyName
in prop:
199 if isinstance(prop, list):
201 if isinstance(item, dict)
and keyName == item[
"name"]
and fieldName
in item:
202 ret = item[fieldName]
◆ isInProperties()
def dc.EventObjects.Site.isInProperties |
( |
|
prop, |
|
|
|
keyName |
|
) |
| |
|
static |
Definition at line 172 of file EventObjects.py.
172 def isInProperties(prop, keyName):
175 if isinstance(prop, dict)
and keyName
in prop:
178 if isinstance(prop, list):
180 if isinstance(item, dict)
and keyName == item[
"name"]:
◆ rewriteFields()
def dc.EventObjects.Site.rewriteFields |
( |
|
self, |
|
|
|
siteObj, |
|
|
|
addListFields = True |
|
) |
| |
Definition at line 151 of file EventObjects.py.
151 def rewriteFields(self, siteObj, addListFields=True):
152 excludeFields = [
"urls",
"filters",
"properties"]
153 for field
in siteObj.__dict__:
154 if field
not in excludeFields
and siteObj.__dict__[field]
is not None:
155 self.__dict__[field] = siteObj.__dict__[field]
156 for field
in excludeFields:
158 if self.__dict__[field]
is not None and siteObj.__dict__[field]
is not None:
159 self.__dict__[field] += siteObj.__dict__[field]
160 elif siteObj.__dict__[field]
is not None:
161 self.__dict__[field] = []
162 self.__dict__[field] += siteObj.__dict__[field]
163 elif siteObj.__dict__[field]
is not None:
164 self.__dict__[field] = siteObj.__dict__[field]
◆ avgSpeed
dc.EventObjects.Site.avgSpeed |
◆ avgSpeedCounter
dc.EventObjects.Site.avgSpeedCounter |
◆ categoryId
dc.EventObjects.Site.categoryId |
◆ cDate
dc.EventObjects.Site.cDate |
◆ collectedURLs
dc.EventObjects.Site.collectedURLs |
◆ contents
dc.EventObjects.Site.contents |
◆ DEFAULT_CATEGORY_ID
int dc.EventObjects.Site.DEFAULT_CATEGORY_ID = 0 |
|
static |
◆ DEFAULT_PRIORITY
int dc.EventObjects.Site.DEFAULT_PRIORITY = 100 |
|
static |
◆ deletedURLs
dc.EventObjects.Site.deletedURLs |
◆ description
dc.EventObjects.Site.description |
◆ errorMask
dc.EventObjects.Site.errorMask |
◆ errors
dc.EventObjects.Site.errors |
◆ FETCH_TYPE_AUTO
int dc.EventObjects.Site.FETCH_TYPE_AUTO = 7 |
|
static |
◆ FETCH_TYPE_DYNAMIC
int dc.EventObjects.Site.FETCH_TYPE_DYNAMIC = 2 |
|
static |
◆ FETCH_TYPE_EXTERNAL
int dc.EventObjects.Site.FETCH_TYPE_EXTERNAL = 3 |
|
static |
◆ FETCH_TYPE_STATIC
int dc.EventObjects.Site.FETCH_TYPE_STATIC = 1 |
|
static |
◆ fetchType
dc.EventObjects.Site.fetchType |
◆ filters
dc.EventObjects.Site.filters |
◆ httpTimeout
dc.EventObjects.Site.httpTimeout |
◆ id
◆ iterations
dc.EventObjects.Site.iterations |
◆ maxErrors
dc.EventObjects.Site.maxErrors |
◆ maxResources
dc.EventObjects.Site.maxResources |
◆ maxResourceSize
dc.EventObjects.Site.maxResourceSize |
◆ maxURLs
dc.EventObjects.Site.maxURLs |
◆ maxURLsFromPage
dc.EventObjects.Site.maxURLsFromPage |
◆ moveURLs
dc.EventObjects.Site.moveURLs |
◆ newURLs
dc.EventObjects.Site.newURLs |
◆ priority
dc.EventObjects.Site.priority |
◆ processingDelay
dc.EventObjects.Site.processingDelay |
◆ properties
dc.EventObjects.Site.properties |
◆ recrawlDate
dc.EventObjects.Site.recrawlDate |
◆ recrawlPeriod
dc.EventObjects.Site.recrawlPeriod |
◆ requestDelay
dc.EventObjects.Site.requestDelay |
◆ resources
dc.EventObjects.Site.resources |
◆ size
dc.EventObjects.Site.size |
◆ state
dc.EventObjects.Site.state |
◆ STATE_ACTIVE
int dc.EventObjects.Site.STATE_ACTIVE = 1 |
|
static |
◆ STATE_CLEANED
int dc.EventObjects.Site.STATE_CLEANED = 7 |
|
static |
◆ STATE_CLEANUP_TASK
int dc.EventObjects.Site.STATE_CLEANUP_TASK = 8 |
|
static |
◆ STATE_DELETE_TASK
int dc.EventObjects.Site.STATE_DELETE_TASK = 5 |
|
static |
◆ STATE_DELETED
int dc.EventObjects.Site.STATE_DELETED = 4 |
|
static |
◆ STATE_DISABLED
int dc.EventObjects.Site.STATE_DISABLED = 2 |
|
static |
◆ STATE_NOT_FOUND
int dc.EventObjects.Site.STATE_NOT_FOUND = 9 |
|
static |
◆ STATE_RESTART
int dc.EventObjects.Site.STATE_RESTART = 6 |
|
static |
◆ STATE_SUSPENDED
int dc.EventObjects.Site.STATE_SUSPENDED = 3 |
|
static |
◆ tcDate
dc.EventObjects.Site.tcDate |
◆ tcDateProcess
dc.EventObjects.Site.tcDateProcess |
◆ uDate
dc.EventObjects.Site.uDate |
◆ urls
dc.EventObjects.Site.urls |
◆ urlType
dc.EventObjects.Site.urlType |
◆ userId
dc.EventObjects.Site.userId |
The documentation for this class was generated from the following file: