标签：else box blog spider extra cti gen crawl href
[TOC]
###2017-02-08 01:19:09 Scrapy: pk5_mylist.md> Save the records with MongoDB
#### settings.py
```
# -*- coding: utf-8 -*-
BOT_NAME = ‘bengbeng‘
SPIDER_MODULES = [‘bengbeng.spiders‘]
NEWSPIDER_MODULE = ‘bengbeng.spiders‘
ROBOTSTXT_OBEY = True
ITEM_PIPELINES = {
‘bengbeng.pipelines.BengbengPipeline‘: 300,
}
DOWNLOADER_MIDDLEWARES = {
‘scrapy.downloadermiddlewares.useragent.UserAgentMiddleware‘:None,
‘bengbeng.middlewares.RotateUserAgentMiddleware‘:400,
}
DOWNLOAD_DELAY = 0.2
COOKIES_ENABLED = True
MONGODB_HOST = ‘127.0.0.1‘
MONGODB_PORT = 27017
MONGODB_DBNAME = ‘bengbeng‘
MONGODB_COLLECTION = ‘scrapy_pk5_mylist‘
```
#### items.py
```
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class BengbengItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
# pm = pk5_mylist
pm_betid = scrapy.Field()
pm_result = scrapy.Field()
pm_result_rate = scrapy.Field()
pm_rate_bao = scrapy.Field()
pm_rate_dui = scrapy.Field()
pm_rate_shun = scrapy.Field()
pm_rate_ban = scrapy.Field()
pm_rate_za = scrapy.Field()
```
#### pipelines.py
```
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don‘t forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
from scrapy.conf import settings
import pymongo
class BengbengPipeline(object):
def __init__(self):
bengbengHost = settings[‘MONGODB_HOST‘]
bengbengPort = settings[‘MONGODB_PORT‘]
bengbengdbName = settings[‘MONGODB_DBNAME‘]
bengbengClient = pymongo.MongoClient(host=bengbengHost, port=bengbengPort)
bengbengtdb = bengbengClient[bengbengdbName]
self.postbengbeng = bengbengtdb[settings[‘MONGODB_COLLECTION‘]]
def process_item(self, bengbengitem, spider):
# self.postbengbeng.insert({‘bengbeng_xflink‘:bengbengitem[‘bengbeng_xflink‘]})
if bengbengitem[‘pm_betid‘] != ‘‘:
bengbeng_pk5_result = dict(bengbengitem)
# print(item[‘mm6xx_title‘])
# try to ignore the same URLs before insert into DB .
if self.postbengbeng.find({‘pm_betid‘:bengbengitem[‘pm_betid‘]}).count() == 0:
print(‘{0}‘.format(bengbeng_pk5_result))
self.postbengbeng.insert(bengbeng_pk5_result)
else:
# if data was found , then update
# bengbeng_pk5_result.pop(‘_id‘)
print("Record was Found ,Update!".center(40,‘*‘))
result = self.postbengbeng.find_one({‘pm_betid‘:bengbengitem[‘pm_betid‘]},{‘pm_result‘:1})
bengbengitem[‘pm_result‘] = result[‘pm_result‘]
# get the pm_result_rate
bengbengitem[‘pm_result_rate‘] = bengbengitem[‘pm_rate_{0}‘.format(result[‘pm_result‘])]
bengbeng_pk5_result = dict(bengbengitem)
# Update : remove the old records , Insert the new one
self.postbengbeng.remove({‘pm_betid‘:bengbengitem[‘pm_betid‘]})
print(‘Update: {0}‘.format(bengbeng_pk5_result))
self.postbengbeng.insert(bengbeng_pk5_result)
return bengbengitem
```
#### pk5_mylist.py
```
# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from scrapy.http.request import Request
from scrapy.http import Request
from scrapy import Spider
from scrapy.selector import Selector
from bengbeng.items import BengbengItem
import re
import time
# try to list xpath
xpath_betid = ‘//*[@id="pkBox"]/ul/*[@class="jl1"]/text()‘
xpath_result = ‘//*[@id="pkBox"]/ul/*[@class="jl3"]/img/@src‘
xpath_all_rate = ‘//*[@id="pkBox"]/ul/*[@class="ck2"]/text()‘
xpath_rate_betid = ‘//*[@id="pkBox"]/div[4]/span[1]/font/text()‘
class Pk5MylistSpider(scrapy.Spider):
name = "pk5_mylist"
allowed_domains = ["bengbeng.com"]
start_urls = [‘http://www.bengbeng.com/pk5mylist.php?p=1‘]
my_cookies = {‘PHPSESSID‘: ‘0gl0onrnocb149v3jcmhpdk3k0‘}
pk5_mylist_item = BengbengItem()
for i in range(2,33): # 2,31
start_urls.append(‘http://www.bengbeng.com/pk5mylist.php?p={0}‘.format(i))
def goForSecondPage(self, response):
all_rate = Selector(response).xpath(xpath_all_rate).extract()
rate_betid = Selector(response).xpath(xpath_rate_betid).extract()
#self.pk5_mylist_item = BengbengItem()
self.pk5_mylist_item[‘pm_betid‘] = rate_betid[0]
self.pk5_mylist_item[‘pm_rate_bao‘] = all_rate[0]
self.pk5_mylist_item[‘pm_rate_dui‘] = all_rate[1]
self.pk5_mylist_item[‘pm_rate_shun‘] = all_rate[2]
self.pk5_mylist_item[‘pm_rate_ban‘] = all_rate[3]
self.pk5_mylist_item[‘pm_rate_za‘] = all_rate[4]
yield self.pk5_mylist_item
#print(self.pk5_mylist_item)
# Reload spiders with new cookies
def start_requests(self):
for url in self.start_urls:
yield Request(url, cookies=self.my_cookies)
def parse(self, response):
all_betid = Selector(response).xpath(xpath_betid).extract()
all_result = Selector(response).xpath(xpath_result).extract()
#self.pk5_mylist_item = BengbengItem()
dict_result = {
‘bz‘:‘bao‘, # Bao
‘dz‘:‘dui‘, # Dui
‘sz‘:‘shun‘, # Shun
‘bs‘:‘ban‘, # Ban
‘zl‘:‘za‘, # Za
}
result_search = re.compile(‘_(\D+)\.‘)
if len(all_result) == 29:
j = 1
for i in range(29):
betid = all_betid[j]
result = dict_result[result_search.findall(all_result[i])[0]]
self.pk5_mylist_item[‘pm_betid‘] = betid
self.pk5_mylist_item[‘pm_result‘] = result
yield self.pk5_mylist_item
url = ‘http://www.bengbeng.com/pk5mdetail.php?no=‘ + betid
yield Request(url,cookies=self.my_cookies,callback=self.goForSecondPage)
j += 1
#time.sleep(0.6)
else:
for i in range(30):
betid = all_betid[i]
result = dict_result[result_search.findall(all_result[i])[0]]
self.pk5_mylist_item[‘pm_betid‘] = betid
self.pk5_mylist_item[‘pm_result‘] = result
yield self.pk5_mylist_item
url = ‘http://www.bengbeng.com/pk5mdetail.php?no=‘ + betid
yield Request(url,cookies=self.my_cookies,callback=self.goForSecondPage)
#time.sleep(0.6)
```
#### Run:
#### Records in DB
```
{
"_id" : ObjectId("5899fac96f59de2268c28918"),
"pm_rate_ban" : "2.7767",
"pm_rate_dui" : "3.7002",
"pm_rate_bao" : "100.8169",
"pm_rate_za" : "3.3057",
"pm_rate_shun" : "16.6743",
"pm_betid" : "463645",
"pm_result" : "ban",
"pm_result_rate" : "2.7767"
}
/* 2 */
{
"_id" : ObjectId("5899fac86f59de2268c28917"),
"pm_rate_ban" : "2.7797",
"pm_rate_dui" : "3.7823",
"pm_rate_bao" : "113.3838",
"pm_rate_za" : "3.3606",
"pm_rate_shun" : "13.7679",
"pm_betid" : "463644",
"pm_result" : "shun",
"pm_result_rate" : "13.7679"
}
```
2017-02-08 01:19:09 Scrapy: pk5_mylist
标签：else box blog spider extra cti gen crawl href
原文地址：http://www.cnblogs.com/topshooter/p/6441464.html
