当前位置:Gxl网 > 前端开发 > 爬取小程序所有教程scrapy

爬取小程序所有教程scrapy

时间:2021-07-01 10:21:17 帮助过:10人阅读

setting:

from fake_useragent import UserAgent

BOT_NAME = ‘wxapp‘

SPIDER_MODULES = [‘wxapp.spiders‘]
NEWSPIDER_MODULE = ‘wxapp.spiders‘

ROBOTSTXT_OBEY = False

DOWNLOAD_DELAY = 1

DEFAULT_REQUEST_HEADERS = {
  ‘Accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8‘,
  ‘User-Agent‘: str(UserAgent().random),
}

ITEM_PIPELINES = {
   ‘wxapp.pipelines.WxappPipeline‘: 300,
}

 

wxapp_spider

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from wxapp.items import WxappItem

class WxappSpiderSpider(CrawlSpider):
    name = ‘wxapp_spider‘
    allowed_domains = [‘wxapp-union.com‘]
    start_urls = [‘https://www.wxapp-union.com/portal.php?mod=list&catid=2&page=1‘]

    rules = (
        Rule(LinkExtractor(allow=r‘.+mod=list&catid=2&page=\d‘), follow=True),
        Rule(LinkExtractor(allow=r".+article-.+\.html"),callback="parse_detail",
             follow=False)
    )

    def parse_detail(self, response):
        title = response.xpath("//h1[@class=‘ph‘]/text()").get()
        author_p = response.xpath("//p[@class=‘authors‘]")
        author = author_p.xpath(".//a/text()").get()
        time = author_p.xpath(".//span[@class = ‘time‘]/text()").get()
        article = response.xpath("//td[@id=‘article_content‘]//text()").getall()
        article = "".join(article).strip()
        print(title, author, time)
        print(article)
        item = WxappItem(title=title,author=author,time=time,content=article)
        yield item

items.py:

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class WxappItem(scrapy.Item):
    title = scrapy.Field()
    author = scrapy.Field()
    time = scrapy.Field()
    content = scrapy.Field()

pipelines.py:

# Define your item pipelines here
#
# Don‘t forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html


# useful for handling different item types with a single interface
from itemadapter import ItemAdapter

from scrapy.exporters import JsonLinesItemExporter
class WxappPipeline:
    def __init__(self):
        self.fp = open("wxjc.json","wb")
        self.export = JsonLinesItemExporter(self.fp,ensure_ascii=False,encoding = ‘utf-8‘)
    def process_item(self, item, spider):
        self.export.export_item(item)
        return item
    def close_spider(self,spider):
        self.fp.close()