Python下使用Scrapy爬取网页内容
上周用了一周的时间学习了Python和Scrapy，实现了从0到1完整的网页爬虫实现。研究的时候很痛苦，但是很享受，做技术的嘛。
首先，安装Python，坑太多了，一个个爬。由于我是windows环境，没钱买mac, 在安装的时候遇到各种各样的问题，确实各种各样的依赖。安装教程不再赘述。如果在安装的过程中遇到 ERROR：需要windows c/c++问题，一般是由于缺少windows开发编译环境，晚上大多数教程是安装一个VisualStudio，太不靠谱了，事实上只要安装一个WindowsSDK就可以了。下面贴上我的爬虫代码：
爬虫主程序：
# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import Request
from zjf.FsmzItems import FsmzItem
from scrapy.selector import Selector
# 圈圈：情感生活
class MySpider(scrapy.Spider):
#爬虫名
name = "MySpider"
#设定域名
allowed_domains = ["nvsheng.com"]
#爬取地址
start_urls = []
#flag
x = 0
#爬取方法
def parse(self, response):
item = FsmzItem()
sel = Selector(response)
item['title'] = sel.xpath('//h1/text()').extract()
item['text'] = sel.xpath('//*[@class="content"]/p/text()').extract()
item['imags'] = sel.xpath('//div[@id="content"]/p/a/img/@src|//div[@id="content"]/p/img/@src').extract()
if MySpider.x == 0:
page_list = MySpider.getUrl(self,response)
for page_single in page_list:
yield Request(page_single)
MySpider.x += 1
yield item
#init: 动态传入参数
#命令行传参写法： scrapy crawl MySpider -a start_url="http://some_url"
def __init__(self,*args,**kwargs):
super(MySpider,self).__init__(*args,**kwargs)
self.start_urls = [kwargs.get('start_url')]
def getUrl(self, response):
url_list = []
select = Selector(response)
page_list_tmp = select.xpath('//div[@class="viewnewpages"]/a[not(@class="next")]/@href').extract()
for page_tmp in page_list_tmp:
if page_tmp not in url_list:
url_list.append("http://www.nvsheng.com/emotion/px/" + page_tmp)
return url_listPipeLines类
# -*- 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 zjf import settings
import json,os,re,random
import urllib.request
import requests, json
from requests_toolbelt.multipart.encoder import MultipartEncoder
class MyPipeline(object):
flag = 1
post_title = ''
post_text = []
post_text_imageUrl_list = []
cs = []
user_id= ''
def __init__(self):
MyPipeline.user_id = MyPipeline.getRandomUser('37619,18441390,18441391')
#process the data
def process_item(self, item, spider):
#获取随机user_id，模拟发帖
user_id = MyPipeline.user_id
#获取正文text_str_tmp
text = item['text']
text_str_tmp = ""
for str in text:
text_str_tmp = text_str_tmp + str
# print(text_str_tmp)
#获取标题
if MyPipeline.flag == 1:
title = item['title']
MyPipeline.post_title = MyPipeline.post_title + title[0]
#保存并上传图片
text_insert_pic = ''
text_insert_pic_w = ''
text_insert_pic_h = ''
for imag_url in item['imags']:
img_name = imag_url.replace('/','').replace('.','').replace('|','').replace(':','')
pic_dir = settings.IMAGES_STORE + '%s.jpg' %(img_name)
urllib.request.urlretrieve(imag_url,pic_dir)
#图片上传，返回json
upload_img_result = MyPipeline.uploadImage(pic_dir,'image/jpeg')
#获取json中保存图片路径
text_insert_pic = upload_img_result['result']['image_url']
text_insert_pic_w = upload_img_result['result']['w']
text_insert_pic_h = upload_img_result['result']['h']
#拼接json
if MyPipeline.flag == 1:
cs_json = {"c":text_str_tmp,"i":"","w":text_insert_pic_w,"h":text_insert_pic_h}
else:
cs_json = {"c":text_str_tmp,"i":text_insert_pic,"w":text_insert_pic_w,"h":text_insert_pic_h}
MyPipeline.cs.append(cs_json)
MyPipeline.flag += 1
return item
#spider开启时被调用
def open_spider(self,spider):
pass
#sipder 关闭时被调用
def close_spider(self,spider):
strcs = json.dumps(MyPipeline.cs)
jsonData = {"apisign":"99ea3eda4b45549162c4a741d58baa60","user_id":MyPipeline.user_id,"gid":30,"t":MyPipeline.post_title,"cs":strcs}
MyPipeline.uploadPost(jsonData)
#上传图片
def uploadImage(img_path,content_type):
"uploadImage functions"
#UPLOAD_IMG_URL = "http://api.qa.douguo.net/robot/uploadpostimage"
UPLOAD_IMG_URL = "http://api.douguo.net/robot/uploadpostimage"
# 传图片
#imgPath = 'D:\pics\http___img_nvsheng_com_uploads_allimg_170119_18-1f1191g440_jpg.jpg'
m = MultipartEncoder(
# fields={'user_id': '192323',
# 'images': ('filename', open(imgPath, 'rb'), 'image/JPEG')}
fields={'user_id': MyPipeline.user_id,
'apisign':'99ea3eda4b45549162c4a741d58baa60',
'image': ('filename', open(img_path , 'rb'),'image/jpeg')}
)
r = requests.post(UPLOAD_IMG_URL,data=m,headers={'Content-Type': m.content_type})
return r.json()
def uploadPost(jsonData):
CREATE_POST_URL = "http://api.douguo.net/robot/uploadimagespost" reqPost = requests.post(CREATE_POST_URL,data=jsonData)
def getRandomUser(userStr):
user_list = []
user_chooesd = ''
for user_id in str(userStr).split(','):
user_list.append(user_id)
userId_idx = random.randint(1,len(user_list))
user_chooesd = user_list[userId_idx-1]
return user_chooesd字段保存Items类
# -*- 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 FsmzItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
title = scrapy.Field()
#tutor = scrapy.Field()
#strongText = scrapy.Field()
text = scrapy.Field()
imags = scrapy.Field()在命令行里键入
scrapy crawl MySpider -a start_url="www.aaa.com"
这样就可以爬取aaa.com下的内容了