最近分别使用了scrapy和requests对内涵社区的爬取,这个网站比较简单,并斌那个没有什反爬策略,简单的思路就是获取数据的网页远吗对其中的json数据解析,然后存储数据。
下面是scrapy的源码
# -*- coding: utf-8 -*-
import json
import scrapy
from neihan.items import NeihanItem
class XmSpiderSpider(scrapy.Spider):
name = "xm_spider"
allowed_domains = ["neihanshequ.com/"]
start_urls = ['http://neihanshequ.com/joke/?is_json=1&app_name=neihanshequ_web&max_time=1507809901.0']
def parse(self, response):
sites = json.loads(response.body_as_unicode())
max_num = sites['data']['max_time']
for group in sites ['data']['data']:
item = NeihanItem()
item['data'] = group['group']['text']
item['title'] = group['group']['user']['name']
yield item
# print(title ,data)
max_url = 'http://neihanshequ.com/joke/?is_json=1&app_name=neihanshequ_web&' + str(max_num)
yield scrapy.Request(url= max_url ,callback=self.parse,dont_filter= True )
# -*- 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 NeihanItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
title = scrapy.Field()
data = scrapy.Field()
# -*- 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 pymongo
from scrapy.conf import settings
class NeihanPipeline(object):
def __init__(self):
host = settings['MONGODB_HOST']
port = settings['MONGODB_PORT']
dbName = settings['MONGODB_DBNAME']
client = pymongo.MongoClient(host=host, port=port)
tdb = client[dbName]
self.post = tdb[settings['MONGODB_DOCNAME']]
def process_item(self, item, spider):
neihan = dict(item)
self.post.insert(neihan)
return item
# -*- coding: utf-8 -*-
# Scrapy settings for neihan 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 = 'neihan'
SPIDER_MODULES = ['neihan.spiders']
NEWSPIDER_MODULE = 'neihan.spiders'
MONGODB_HOST = '127.0.0.1'
MONGODB_PORT = 27017
MONGODB_DBNAME = 'neihan'
MONGODB_DOCNAME = 'duanzi'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'neihan (+http://www.yourdomain.com)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# 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',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'
}
# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'neihan.middlewares.NeihanSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'neihan.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 = {
'neihan.pipelines.NeihanPipeline': 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'
下面的是requests的方法
# coding:utf-8
import json
import requests
from bs4 import BeautifulSoup
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36"
" (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36",
}
url = 'http://neihanshequ.com/joke/?is_json=1&app_name=neihanshequ_web&max_time=1507794658.0'
def parse_url(url):
response = requests.get(url, headers=headers).json()
# soup = BeautifulSoup(response.text,'lxml')
# html = json.loads(str(response) )
for group in response['data']['data']:
data = group['group']['text']
print(data)
save_data(data)
max_num = str(response['data']['max_time'])
max_url = 'http://neihanshequ.com/joke/?is_json=1&app_name=neihanshequ_web&'+max_num
# print(max_url )
parse_url(max_url )
def get_page(url):
try:
str_data = parse_url(url)
except Exception as e:
print(e)
str_data = None
return str_data
def save_data(data_list):
with open('neihan.txt', 'a',encoding= "utf-8")as f:
f.write(data_list + '\n')
# f.closed()
if __name__ =="__main__":
data = get_page(url)