备注(没有该平台账号是进不去的,可参考爬虫实现思路)
spider.py
import scrapy
import json
from bosi.items import BosiItem
class BsSpider(scrapy.Spider):
name = 'bs'
allowed_domains = ['cqie.iflysse.com/']
start_urls = ['http://cqie.iflysse.com/Handler/Report/StuFileList.ashx']
#首次发起请求
def start_requests(self):
#翻页的url
url = "http://cqie.iflysse.com/Handler/Report/StuFileList.ashx"
headers={
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36",
"Cookie":"userName=xxxxx; ASP.NET_SessionId=n1omhosmkcyjhyhba3meor0e; iflysse_client_sign=0f1d7195-8fca-4abd-b215-2dd2f15636e2; cacheHeader=%e9%bb%84%e5%a4%a9%e6%98%a5%3a1%3a%3a1; td_cookie=3815166223; SessionId=ec81f300-531f-4688-92ee-08af29d1aed5"
}
for i in range(60):
#formdata必须以键值对的形式封装,所以翻页int类型要转为str类型,这个a必须强转,直接用i的话是类型错误
a=str(i*20)
formdata={
'sEcho':'1',
'iColumns':'6',
'sColumns':',,,,,',
'iDisplayStart':a,
'iDisplayLength':'20',
'mDataProp_0':'UserObject',
'bSortable_0':'false',
'mDataProp_1':'Name',
'bSortable_1':'false',
'mDataProp_2':'Email',
'bSortable_2':'false',
'mDataProp_3':'IDCard',
'bSortable_3':'false',
'mDataProp_4':'GenderStr',
'bSortable_4':'false',
'mDataProp_5':'5',
'bSortable_5':'false',
'iSortCol_0':'0',
'sSortDir_0':'asc',
'iSortingCols':'1',
'Action':'0',
'SelectStr':'',
'ClassType':'0',
'ClassID':'-1',
}
#FormRequest相当于是手动指定post。
yield scrapy.FormRequest(url,formdata=formdata,headers=headers, callback=self.parse)
def parse(self, response):
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36",
"Cookie": "userName=xxxxxx; ASP.NET_SessionId=n1omhosmkcyjhyhba3meor0e; iflysse_client_sign=0f1d7195-8fca-4abd-b215-2dd2f15636e2; cacheHeader=%e9%bb%84%e5%a4%a9%e6%98%a5%3a1%3a%3a1; td_cookie=3815166223; SessionId=ec81f300-531f-4688-92ee-08af29d1aed5"
}
#页面数据是json格式,所以我们需要用json.loads
dict_data=json.loads(response.text)
for item1 in dict_data['aaData']:
item=BosiItem()
#学号
item["UserObject"]=item1["UserObject"]
#姓名
item["UserName"]=item1["UserName"]
#邮箱
item["Email"]=item1["Email"]
#身份证
item["IDCard"]=item1["IDCard"]
#性别
item["GenderStr"]=item1["GenderStr"]
#档案链接
item["ObjectID"]=item1["ObjectID"]
yield item
print(item)
#档案页链接
url = "http://cqie.iflysse.com/Handler/Public/StuFile.ashx"
formdata1 = {
"Action": '2',
#档案页链接实际是一串加密内容,通过ajax加载详情页数据
"ID":item["ObjectID"]
} #meta:请求传参
yield scrapy.FormRequest(url, formdata=formdata1, headers=headers, callback=self.sun_parse, meta={
"item": item})
def sun_parse(self,response):
dict_data2=json.loads(response.text)
for item2 in dict_data2["Data"]["CourseList"]:
item=response.meta["item"]
response
#课程名称
item["CourseName"]=item2["CourseName"]
#时间
item["DateStr"]=item2["DateStr"]
#学习时长
item["LearnTimeStr"]=item2["LearnTimeStr"]
#进度
item["ProgressStr"]=item2["ProgressStr"]
#正确率
item["CorrectRateStr"]=item2["CorrectRateStr"]
#编译次数
item["CompileNum"]=item2["CompileNum"]
print(item)
yield item
main.py(这样就不用在终端运行)
from scrapy.cmdline import execute
execute('scrapy crawl bs'.split())
item.py
# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html
import scrapy
class BosiItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
# 学号
UserObject = scrapy.Field()
# 姓名
UserName = scrapy.Field()
# 邮箱
Email = scrapy.Field()
# 身份证
IDCard = scrapy.Field()
# 性别
GenderStr = scrapy.Field()
# 档案链接
ObjectID = scrapy.Field()
# 课程名称
CourseName=scrapy.Field()
# 时间
DateStr = scrapy.Field()
# 学习时长
LearnTimeStr = scrapy.Field()
# 进度
ProgressStr = scrapy.Field()
# 正确率
CorrectRateStr = scrapy.Field()
# 编译次数
CompileNum = 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
import pymysql
class BosiPipeline:
def process_item(self, item, spider):
conn=pymysql.connect(host="localhost",db="qu",user="root",passwd="123456",charset="utf8")
cur=conn.cursor()
# 学号
UserObject = item["UserObject"]
# 姓名
UserName = item["UserName"]
# 邮箱
Email= item["Email"]
# 身份证
IDCard= item["IDCard"]
# 性别
GenderStr = item["GenderStr"]
# 档案链接
ObjectID = item["ObjectID"]
# 课程名称
CourseName = item["CourseName"]
# 时间
DateStr= item["DateStr"]
# 学习时长
LearnTimeStr= item["LearnTimeStr"]
# 进度
ProgressStr= item["ProgressStr"]
# 正确率
CorrectRateStr = item["CorrectRateStr"]
# 编译次数
CompileNum = item["CompileNum"]
sql1="insert into bs(UserObject,UserName,Email,IDCard,GenderStr,ObjectID)values ('%s','%s','%s','%s','%s','%s')"%(UserObject,UserName,Email,IDCard,GenderStr,ObjectID)
sql2="insert into dn(UserObject,CourseName,DateStr,LearnTimeStr,ProgressStr,CorrectRateStr,CompileNum)values ('%s','%s','%s','%s','%s','%s','%s')"%(UserObject,CourseName,DateStr,LearnTimeStr,ProgressStr,CorrectRateStr,CompileNum)
print(sql1)
print(sql2)
cur.execute(sql1)
cur.execute(sql2)
conn.commit()
cur.close()
conn.close()
return item
settings.py
# Scrapy settings for bosi 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 = 'bosi'
SPIDER_MODULES = ['bosi.spiders']
NEWSPIDER_MODULE = 'bosi.spiders'
#打印日志
LOG_LEVEL="ERROR"
FEED_EXPROT_ENCODING="UTF-8"
# Crawl responsibly by identifying yourself (and your website) on the user-agent
MY_USER_AGENT = [
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
"Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
"Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
"Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
"Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
"Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
"Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 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',
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36",
"Cookie":"userName=xxxxxx; ASP.NET_SessionId=n1omhosmkcyjhyhba3meor0e; iflysse_client_sign=0f1d7195-8fca-4abd-b215-2dd2f15636e2; cacheHeader=%e9%bb%84%e5%a4%a9%e6%98%a5%3a1%3a%3a1; td_cookie=3363675142; SessionId=82413c7c-ec2b-45e1-bd9e-d763342bff3d"
}
# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'bosi.middlewares.BosiSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
'bosi.middlewares.BosiDownloaderMiddleware': 543,
'scrapy.downloadermiddleware.useragent.UserAgentMiddleware': None,
'myproject.middlewares.MyUserAgentMiddleware': 400,
}
# 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 = {
'bosi.pipelines.BosiPipeline': 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'