冰峰雪晴

如何绕过登录抓取js动态加载网页数据[Python]

时间：2018-11-24 ┊ 阅读：6,970 次 ┊ 标签: 开发 , 编程 , 经验

今天经历了一翻折腾，把一个需要登录网站并js动态加载的数据一一给抓下来了。

首先，登录时有cookie,我们需要把cookie保存下来，用urllib2构建request时加入header信息，这时还多了一点，虚构了浏览器信息，让服务器以为是正常的浏览器发起的请求，这样可以绕过简单的反爬虫策略。

等用cookie搞定了登录，发现网页是js动态加载，抓取失败！
搜索了一下，发现两种方法：

1. 用工具，构建webdriver，用chrome或firefox来打开网页，缺点效率太低。
2. 分析网页加载过程，通过response信息找到网页加载时调用的api或服务地址，这个较烦琐麻烦，不过找到可是一劳永逸，用python全部能过后台抓取成为可能。

在几十个请求中，最后找到了后台加载数据服务地址，找到了规律，然后用id进行拼接得到完整地址，就可以构造请求了。
服务器返回的数据竟然不是json数据，而是xml，赶紧研究一下xml解析方法，我选择了minidom来解析，感觉看着舒服。

然后遇到了空标签问题，在网页上没有评论的时候，标签是空的时候，就报错了，因为直接访问list，这时会报out of index error。简单粗暴直接try然后跳过。

抓取的数据写入csv，download的附件分别保存到以id建的小文件夹下面。

时间的格式化，打印出含毫秒的长时期字符，和robot测试工具输出提示一致。

最后把中间生成的临时xml文件删除了。哈哈

代码：

#!/usr/bin/python
# -*- coding:utf-8 -*-

import urllib2
import xml.dom.minidom
import os
import csv
import time

def get_timestamp():
    ct = time.time()
    local_time = time.localtime(ct)
    time_head = time.strftime("%Y%m%d %H:%M:%S", local_time)
    time_secs = (ct - long(ct)) * 1000
    timestamp = "%s.%03d" % (time_head, time_secs)
    return timestamp

# create request user-agent header
userAgent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'
cookie = '...0000Y3Pwq2s9BdZn8e0zpTDmkVv:-1...'
uaHeaders = {'User-Agent': userAgent, 'Cookie': cookie}

# item url string connection
itemUrlHead = "https://api.amkevin.com:8888/ccm/service/com.amkevin.team.workitem.common.internal.rest.IWorkItemRestService/workItemDT88?includeHistory=false&id="
itemUrlId = "99999"
itemUrlTail = "&projectAreaItemId=_hnbI8sMnEeSExMMeBFetbg"
itemUrl = itemUrlHead + itemUrlId + itemUrlTail

# send request with user-agent header
request = urllib2.Request(itemUrl, headers=uaHeaders)
response = urllib2.urlopen(request)
xmlResult = response.read()

# prepare the xml file
curPath = os.getcwd()
curXml = curPath + '/' + itemUrlId + '.xml'
if os.path.exists(curXml):
    os.remove(curXml)
curAttObj = open(curXml, 'w')
curAttObj.write(xmlResult)
curAttObj.close()

# print xmlItem

# parse response xml file
DOMTree = xml.dom.minidom.parse(curXml)
xmlDom = DOMTree.documentElement

# prepare write to csv
csvHeader = ["ID", "Creator", "Creator UserID", "Comment Content", "Creation Date"]
csvRow = []
csvCmtOneFile = curPath + '/rtcComment.csv'
if not os.path.exists(csvCmtOneFile):
    csvObj = open(csvCmtOneFile, 'w')
    csvWriter = csv.writer(csvObj)
    csvWriter.writerow(csvHeader)
    csvObj.close()

# get comments & write to csv file
items = xmlDom.getElementsByTagName("items")
for item in items:
    try:
        if item.hasAttribute("xsi:type"):
            curItem = item.getAttribute("xsi:type")
            if curItem == "workitem.restDTO:CommentDTO":
                curCommentContent = item.getElementsByTagName("content")[0].childNodes[0].data
                curCommentContent = curCommentContent.replace('<synthetic>', '')
                curCommentContent = curCommentContent.replace('</synthetic>', '')
                curCommentCreationDate = item.getElementsByTagName("creationDate")[0].childNodes[0].data
                curCommentCreator = item.getElementsByTagName("creator")[0]
                curCommentCreatorName = curCommentCreator.getElementsByTagName("name")[0].childNodes[0].data
                curCommentCreatorId = curCommentCreator.getElementsByTagName("userId")[0].childNodes[0].data
                csvRow = []
                csvRow.append(itemUrlId)
                csvRow.append(curCommentCreatorName)
                csvRow.append(curCommentCreatorId)
                csvRow.append(curCommentContent)
                csvRow.append(curCommentCreationDate)
                csvObj = open(csvCmtOneFile, 'a')
                csvWriter = csv.writer(csvObj)
                csvWriter.writerow(csvRow)
                csvObj.close()

                # save the attachment file to local dir
                curAttFile = curPath + '/' + itemUrlId
                if not os.path.exists(curAttFile):
                    os.mkdir(curAttFile)
                curAttFile = curPath + '/' + itemUrlId + '/' + itemUrlId + '.csv'
                if os.path.exists(curAttFile):
                    curCsvObj = open(curAttFile, 'a')
                    curCsvWriter = csv.writer(curCsvObj)
                    curCsvWriter.writerow(csvRow)
                else:
                    curCsvObj = open(curAttFile, 'w')
                    curCsvWriter = csv.writer(curCsvObj)
                    curCsvWriter.writerow(csvRow)
                curCsvObj.close()
                print get_timestamp() + " :" + "  INFO :" + " write comments to csv success."
    except:
        print get_timestamp() + " :" + "  INFO :" + " parse xml encountered empty element, skipped."
        continue

# get attachment
linkDTOs = xmlDom.getElementsByTagName("linkDTOs")
for linkDTO in linkDTOs:
    try:
        if linkDTO.getElementsByTagName("target")[0].hasAttribute("xsi:type"):
            curAtt = linkDTO.getElementsByTagName("target")[0].getAttribute("xsi:type")
            if curAtt == "workitem.restDTO:AttachmentDTO":
                curAttUrl = linkDTO.getElementsByTagName("url")[0].childNodes[0].data
                curTarget = linkDTO.getElementsByTagName("target")[0]
                curAttName = curTarget.getElementsByTagName("name")[0].childNodes[0].data
                # save the attachment file to local dir
                curAttFolder = curPath + '/' + itemUrlId
                if not os.path.exists(curAttFile):
                    os.mkdir(curAttFolder)
                curAttFile = curPath + '/' + itemUrlId + '/' + curAttName
                curRequest = urllib2.Request(curAttUrl, headers=uaHeaders)
                curResponse = urllib2.urlopen(curRequest)
                curAttRes = curResponse.read()
                if os.path.exists(curAttFile):
                    os.remove(curAttFile)
                curAttObj = open(curAttFile, 'w')
                curAttObj.write(curAttRes)
                curAttObj.close()
                print get_timestamp() + " :" + "  INFO :" + " download attachment [" + curAttName + "] success."
    except:
        print get_timestamp() + " :" + "  INFO :" + " parse xml encountered empty element, skipped."
        continue

    # print linkDTO

# delete temporary xml file
if os.path.exists(curXml):
    os.remove(curXml)

本文固定链接: https://www.amkevin.com/334.html｜冰峰雪晴｜转载请注明出处,谢谢