python scrapy 爬当当数据
scrapy startproject dangdang
cd dangdang
scrapy genspider dangdang "dangdang.com"
核心代码
dangdang.py
# -*- coding: utf-8 -*-
import json
import scrapy
from copy import deepcopy
import json
class DangdangSpider(scrapy.Spider):
name = 'dangdang'
allowed_domains = ['dangdang.com']
start_urls = ['http://e.dangdang.com/list-WY1-dd_sale-0-1.html']
def parse(self, response):
b_list = response.xpath("/html/body/div[5]/div[2]/div[1]/div/div")
item = {}
for first_level in b_list:
item["b_cate_name"] = first_level.xpath(".//a/h3/text()").extract_first()
item["b_cate_href"] = first_level.xpath(".//a/@href").extract_first()
# print(item)
li_list = first_level.xpath("./ul/li")
# 特殊处理
if len(li_list) > 0:
for li in li_list:
item["s_cate_href"] = li.xpath(".//a/@href").extract_first()
item["s_cate_name"] = li.xpath(".//a/h4/text()").extract_first()
item["s_cate_type"] = li.xpath(".//a/h4/@data-type").extract_first()
item["s_books"] = "http://e.dangdang.com/media/api.go?action=mediaCategoryLeaf&promotionType=1" \
"&deviceSerialNo=html5&macAddr=html5&channelType=html5&permanentId" \
"=20200524135342174347312679598555233&returnType=json&channelId=70000" \
"&clientVersionNo=5.8.4&platformSource=DDDS-P&fromPlatform=106&deviceType" \
"=pconline&token=&start=1&end=3&category=" + item[
"s_cate_type"] + "&dimension=dd_sale&order=0 "
yield scrapy.Request(
item["s_books"],
callback=self.parse_book_list,
meta={"item": deepcopy(item)}
)
# print(item)
else:
a_list = first_level.xpath("./ul/a")
for a in a_list:
item["s_cate_href"] = a.xpath("@href").extract_first()
item["s_cate_name"] = a.xpath("./li/text()").extract_first()
item["s_cate_type"] = li.xpath("./li/@data-type").extract_first()
if item["s_cate_type"] is not None:
item["s_books"] = "http://e.dangdang.com/media/api.go?action=mediaCategoryLeaf&promotionType=1" \
"&deviceSerialNo=html5&macAddr=html5&channelType=html5&permanentId" \
"=20200524135342174347312679598555233&returnType=json&channelId=70000" \
"&clientVersionNo=5.8.4&platformSource=DDDS-P&fromPlatform=106&deviceType" \
"=pconline&token=&start=1&end=3&category=" + item[
"s_cate_type"] + "&dimension=dd_sale&order=0 "
yield scrapy.Request(
item["s_books"],
callback=self.parse_book_list,
meta={"item": deepcopy(item)})
def parse_book_list(self, response):
item = response.meta["item"]
data = json.loads(response.text)
book_list = data['data'].get('saleList', {})
# print(book_list)
if len(book_list) > 0:
for book in book_list:
item["book_author"] = book['mediaList'][0]["authorPenname"]
item["book_title"] = book['mediaList'][0]["title"]
print(item)
setting.py
# -*- coding: utf-8 -*-
# Scrapy settings for book 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
from datetime import datetime
BOT_NAME = 'book'
SPIDER_MODULES = ['book.spiders']
NEWSPIDER_MODULE = 'book.spiders'
LOG_LEVEL = "WARNING"
USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
LOG_FILE="log.txt"
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'book (+http://www.yourdomain.com)'
# 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 = {
# 'book.middlewares.BookSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'book.middlewares.BookDownloaderMiddleware': 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 = {
# 'book.pipelines.BookPipeline': 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'
