BaiduSpider，JDCommentsSpider1

import scrapy


class BaiduSpider(scrapy.Spider):
    # 每个爬虫的名称 不能重复 用于启动爬虫
    name = 'BaiduSpider'
    # 爬虫所能允许"活动范围"
    allowed_domains = ['baidu.com']
    # 指定爬虫启动的url
    start_urls = ['https://www.baidu.com']

    # 处理响应
    def parse(self, response, **kwargs):
        print(response.text)

settings.py下:

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

PS D:\python\projects\pythonProject16\ScrapyDemo> scrapy crawl BaiduSpider

import scrapy


class JDCommentsSpider(scrapy.Spider):
    # 每个爬虫的名称 不能重复 用于启动爬虫
    name = 'JDCommentsSpider'
    # 爬虫所能允许"活动范围"
    allowed_domains = ['jd.com']

    # 手动启动爬虫
    def start_requests(self):
        url_format = 'https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=100008348542&score=0&sortType=5&page=1&pageSize=10&isShadowSku=0&rid=0&fold=1'
        for page in range(1):
            url = url_format.format(page=page)
            # 手动的发起请求
            yield scrapy.Request(url=url, callback=self.my_parse)

     # 定义自己的解析方式
     def my_parse(self, response):
        # 解析数据
        # print(response.text)
        pass


from scrapy.cmdline import execute

if __name__ == '__main__':
    execute("scrapy crawl JDCommentsSpider".split())

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

import scrapy


class ScrapydemoItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    pass


# 明确爬取的目标结构
class JDCommentItem(scrapy.Item):
    id = scrapy.field()
    nickname = scrapy.field()
    score = scrapy.field()
    content = scrapy.field()
    creationTime = scrapy.field()

import re

json_str1 = 'fetchJSON_comment98({"jwotestProdect":null,"score":0});'

# 分组
regex = '(fetchJSON_comment98\()(.*)(\);)'
re_grps = re.match(regex, json_str1)
print(re_grps)
print(re_grps.group(0))
print(re_grps.group(1))
print(re_grps.group(2))
print(re_grps.group(3))