scrapy获取气象预警

scrapy获取气象预警

qxyj.py:

# -*- coding: utf-8 -*-
import datetime,time
from bs4 import BeautifulSoup
import requests
import scrapy
from QXYJ.items import QxyjItem

class QxyjSpider(scrapy.Spider):
    name = 'qxyj'
    allowed_domains = ['weather.com.cn']
    # start_urls = ['http://www.weather.com.cn/alarm/newalarmlist.shtml?level=3']
    start_urls = ['http://product.weather.com.cn/alarm/grepalarm_cn.php']

    def parse(self, response):
        items = []
        # 获取发布列表
        result_ = response.text[:-1]
        result = result_.split("=")[-1]
        # 注意:eval转换的时候不能有null，否则会报错，将null赋值为空
        null = ''
        result = eval(result)
        data = result['data']
        length = len(data)
        # 今天的日期
        today = datetime.datetime.now().strftime("%Y%m%d")
        today2 = datetime.datetime.now().strftime("%Y-%m-%d")
        # 内容地址的前半部分
        start_url = 'http://product.weather.com.cn/alarm/webdata/'
        if length>30:
            for i in range(0,30):
                item = QxyjItem()
                # 101100503-20210507103742-6801.html
                end_url = data[i][1]
                # 获取中间的日期
                pub_time = end_url.split("-")[1][:8]
                if pub_time == today:
                    # 由于是js动态加载的不能直接获取
                    # 获取地址http://www.weather.com.cn/alarm/newalarmcontent.shtml?file=1011201-20210507091026-0501.html
                    item['news_url'] = start_url + end_url
                    item['pub_time'] = today2
                    items.append(item)
        else:
            for i in range(0, length):
                item = QxyjItem()
                # 101100503-20210507103742-6801.html
                end_url = data[i][1]
                # 获取中间的日期
                pub_time = end_url.split("-")[1][:8]
                if pub_time == today:
                    # 由于是js动态加载的不能直接获取
                    # 获取地址http://www.weather.com.cn/alarm/newalarmcontent.shtml?file=1011201-20210507091026-0501.html
                    item['news_url'] = start_url + end_url
                    item['pub_time'] = today2
                    items.append(item)

        for item in items:
            time.sleep(1)
            yield scrapy.Request(url=item['news_url'], meta={'meta_1': item}, callback=self.parse_news)

    def parse_news(self, response):
        item = QxyjItem()
        meta_1 = response.meta['meta_1']
        result = response.text
        start_content='<span style="color:#222222;font-family:&quot;microsoftyahei&quot;;white-space:pre-wrap;font-size:16px;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;'
        end_content = '</span>'
        result = result.split("=")[-1]
        result = eval(result)
        news_title = result['head']
        content = result['ISSUECONTENT']
        key_word = result['SIGNALTYPE']
        item['pub_time'] = meta_1['pub_time']
        item['news_title'] = news_title
        item['source'] = '中国天气网'
        item['key_word'] = key_word
        item['is_pub'] = '否'
        item['content'] = start_content + content + end_content
        if len(content) > 150:
            item['news_guide'] = content[:100] + "......"
        else:
            item['news_guide'] = content
        yield item

items.py：

import scrapy

class QxyjItem(scrapy.Item):
    # define the fields for your item here like:
    # 标题
    news_title = scrapy.Field()
    # 来源
    source = scrapy.Field()
    # 关键字
    key_word = scrapy.Field()
    # 文章导读
    news_guide = scrapy.Field()
    # 正文
    content = scrapy.Field()
    # 文章地址
    news_url = scrapy.Field()
    # 发布时间
    pub_time = scrapy.Field()
    # 上传情况
    is_pub = scrapy.Field()

pipelines.py：

import json,time
from openpyxl import Workbook

# 转码操作，继承json.JSONEncoder的子类
class MyEncoder(json.JSONEncoder):
    def default(self, o):
        if isinstance(o, bytes):
            return str(o, encoding='utf-8')
        return json.JSONEncoder.default(self, o)

class QxyjPipeline(object):
    def __init__(self):
        self.wb = Workbook()
        self.ws = self.wb.active
        # 创建表头
        self.ws.append(['标题', '来源', '关键字', '文章导读', '正文', '发布时间','是否上传'])
    def process_item(self, item, spider):
        text = [item['news_title'], item['source'], item['key_word'], item['news_guide'],
                item['content'], item['pub_time'],item['is_pub']]
        self.ws.append(text)
        return item
    def close_spider(self, spider):
        time_file = time.strftime("%Y-%m-%d", time.localtime())
        self.wb.save('qxyj'+time_file+'.xlsx')
        print("数据处理完毕，谢谢使用！")

settings.py：

ITEM_PIPELINES = {
   'QXYJ.pipelines.QxyjPipeline': 300,
}
DEFAULT_REQUEST_HEADERS = {
    'User-Agent': 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0);',
  # 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
  # 'Accept-Language': 'en',
}

# 还可以将日志存到本地文件中（可选添加设置）
LOG_FILE = "qxyj.log"
LOG_LEVEL = "DEBUG"
# 包含打印信息也一起写进日志里
LOG_STDOUT = True

# Obey robots.txt rules
ROBOTSTXT_OBEY = False