使用python scrapy爬取天气并导出csv文件

pip install scrapy

scrapy startproject name

scrapy genspider spider_name 域名

import scrapy

class ChangshuSpider(scrapy.Spider):
    name = 'changshu'
    allowed_domains = ['tianqi.2345.com']
    start_urls = ['https://tianqi.2345.com/today-60038.htm']

    def parse(self, response):
        # 日期、天气状态、温度、风级
        # 利用xpath解析数据、不会xpath的同学可以去稍微学习一下，语法简单
        dates = response.xpath('//a[@class="seven-day-item "]/em/text()').getall()
        states = response.xpath('//a[@class="seven-day-item "]/i/text()').getall()
        temps = response.xpath('//a[@class="seven-day-item "]/span[@class="tem-show"]/text()').getall()
        winds = response.xpath('//a[@class="seven-day-item "]/span[@class="wind-name"]/text()').getall()
        # 返回每条数据
        for date, state, temp, wind in zip(dates,states,temps,winds):
            yield {
                'date' : date,
                'state': state,
                'temp': temp,
                'wind': wind
            }

USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'

ROBOTSTXT_OBEY = False

# Scrapy settings for spider_weather project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'spider_weather'

SPIDER_MODULES = ['spider_weather.spiders']
NEWSPIDER_MODULE = 'spider_weather.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'

# 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 https://docs.scrapy.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 https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'spider_weather.middlewares.SpiderWeatherSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'spider_weather.middlewares.SpiderWeatherDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
# ITEM_PIPELINES = {
#    'spider_weather.pipelines.SpiderWeatherPipeline': 300,
# }

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.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 https://docs.scrapy.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'

scrapy crawl changshu -o weather.csv

from scrapy.conf import settings
from scrapy.contrib.exporter import CsvItemExporter

class MyProjectCsvItemExporter(CsvItemExporter):
def init(self, *args, **kwargs):
delimiter = settings.get(‘CSV_DELIMITER', ‘,')
kwargs[‘delimiter'] = delimiter
fields_to_export = settings.get(‘FIELDS_TO_EXPORT', [])
if fields_to_export :
kwargs[‘fields_to_export'] = fields_to_export
super(MyProjectCsvItemExporter, self).init(*args, **kwargs)

#定义输出格式
FEED_EXPORTERS = {
‘csv': ‘project_name.spiders.csv_item_exporter.MyProjectCsvItemExporter',
}
#指定csv输出字段的顺序
FIELDS_TO_EXPORT = [
‘name',
‘title',
‘info'
]
#指定分隔符
CSV_DELIMITER = ‘,'