爬取某个商品的评价信息
爬虫工具:Scrapy
spider1/spiders/spider1.py
# -*- coding: utf-8 -*-
import logging
import re
from scrapy.selector import Selector
from scrapy.spiders import Spider
from scrapy.utils.response import get_base_url
from spider1.items import FeedbackItem
logger = logging.getLogger('xxx_spider_logger')
class XxxSpider(Spider)
name = "xxx"
allowed_domains = ["xxx.com"]
start_urls = [
"http://feedback.xxx.com/display/productEvaluation.htm?productId=32349005878&ownerMemberId=202654736&companyId=215114749&memberType=seller&startValidDate=&i18n=true"
]
def parse(self, response):
base_url = get_base_url(response)
print('base_url: ' + base_url)
items = []
sel = Selector(response)
feedbacks = sel.xpath('//div[@class="feedback-item clearfix"]')
logger.info('feedbacks length: %i', len(feedbacks))
for feedback in feedbacks:
item = FeedbackItem()
#user_country
fb_user_info = feedback.xpath('div[@class="fb-user-info"]')
item['user_country'] = fb_user_info.xpath('div[@class="user-country"]/b/text()').extract()[0]
# logger.info('user_country: %s', item['user_country'])
#fb_rate_info
fb_main = feedback.xpath('div[@class="fb-main"]')
item['fb_rate_info'] = fb_main.xpath('div[@class="f-rate-info"]/span[@class="star-view"]/span/@style').re('width:(\d+)%')[0]
# logger.info('fb_rate_info: %s', item['fb_rate_info'])
#fb_content
item['fb_content'] = fb_main.xpath('div[@class="f-content"]/dl/dt/span/text()').extract()[0]
# logger.info('fb_content: %s', item['fb_content'])
items.append(item)
return items
spider1/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
from scrapy.item import Item, Field
class FeedbackItem(Item):
user_country = Field()
fb_rate_info = Field()
fb_content = Field()
spider1/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
import json
class XxxPipeline(object):
def __init__(self):
self.file = open('item.json', 'wb')
def process_item(self, item, spider):
line = json.dumps(dict(item)) + "\r\n"
self.file.write(line)
return item
spider1/settings.py
# -*- coding: utf-8 -*-
# Scrapy settings for spider1 project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# http://doc.scrapy.org/en/latest/topics/settings.html
# http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'xxx'
SPIDER_MODULES = ['spider1.spiders']
NEWSPIDER_MODULE = 'spider1.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'spider1 (+http://www.yourdomain.com)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = True
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16
# Disable cookies (enabled by default)
#COOKIES_ENABLED = False
# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False
# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
#}
# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'spider1.middlewares.MyCustomSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'spider1.middlewares.MyCustomDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
'spider1.pipelines.XxxPipeline': 300,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False
# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
相关文章:
电商评价质量评分模型(一)