Python爬虫视频教程零基础小白到scrapy爬虫高手-轻松入门

https://item.taobao.com/item.htm?spm=a1z38n.10677092.0.0.482434a6EmUbbW&id=564564604865

#coding=utf-8
import requests
from bs4 import BeautifulSoup
import urllib.request as ur
import urllib.parse as par
import re #cookie 自动获取
#cookie_start = "entrezSort=pubmed:; "
#cookie_end = "; _ga=GA1.2.82560226.1459065437; _gat=1; ncbi_prevPHID=3971636F6DCF48491459222804198SID; prevselfurl=http%3A//www.ncbi.nlm.nih.gov/; unloadnext=jsevent%3Dunloadnext%26ncbi_pingaction%3Dunload%26eventid%3D1%26jsperf_dns%3D3923%26jsperf_connect%3D252%26jsperf_ttfb%3D310%26jsperf_basePage%3D9%26jsperf_frontEnd%3D4645%26jsperf_navType%3D0%26jsperf_redirectCount%3D0%26maxScroll_x%3D0%26maxScroll_y%3D0%26currScroll_x%3D0%26currScroll_y%3D0%26hasScrolled%3Dfalse%26ncbi_phid%3D3971636F6DCF48491459222804198SID%26sgSource%3Dnative"
pubmed_url = r'http://www.ncbi.nlm.nih.gov/pubmed' pubmed_r = requests.get(pubmed_url)
print(pubmed_r.cookies)
pubmed_cookie_dict = requests.utils.dict_from_cookiejar(pubmed_r.cookies)
print(pubmed_cookie_dict)
cookie = ";".join(["%s=%s" % (k, v) for k, v in pubmed_cookie_dict.items()])
print(cookie) #heads
heads={
"Host":"www.ncbi.nlm.nih.gov",
"Origin":"http://www.ncbi.nlm.nih.gov",
"Referer":"http://www.ncbi.nlm.nih.gov/pubmed",
"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.85 Safari/537.36",
"Cookie": cookie
} kw_url="http://www.ncbi.nlm.nih.gov/pubmed/?term=bone+fracture+&EntrezSystem2.PEntrez.PubMed.Pubmed_PageController.PreviousPageName=results&EntrezSystem2.PEntrez.PubMed.Pubmed_PageController.SpecialPageName=&EntrezSystem2.PEntrez.PubMed.Pubmed_Facets.FacetsUrlFrag=filters%3D&EntrezSystem2.PEntrez.PubMed.Pubmed_Facets.FacetSubmitted=false&EntrezSystem2.PEntrez.PubMed.Pubmed_Facets.BMFacets=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.sPresentation=docsum&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.sPageSize=200&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.sSort=none&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.FFormat=docsum&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.FSort=&email_format=docsum&email_sort=&email_count=20&email_start=1&email_address=&email_subj=bone+fracture+-+PubMed&email_add_text=&EmailCheck1=&EmailCheck2=&coll_start=1&citman_count=20&citman_start=1&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.FileFormat=docsum&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.LastPresentation=docsum&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.Presentation=docsum&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.PageSize=200&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.LastPageSize=200&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.Sort=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.LastSort=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.FileSort=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.Format=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.LastFormat=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.PrevPageSize=200&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.PrevPresentation=docsum&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.PrevSort=&CollectionStartIndex=1&CitationManagerStartIndex=1&CitationManagerCustomRange=false&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_ResultsController.ResultCount=188348&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_ResultsController.RunLastQuery=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Entrez_Pager.cPage=1&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Entrez_Pager.cPage=1&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.sPresentation2=docsum&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.sPageSize2=20&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.sSort2=none&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.FFormat2=docsum&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Pubmed_DisplayBar.FSort2=&email_format2=docsum&email_sort2=&email_count2=20&email_start2=1&email_address2=&email_subj2=bone+fracture+-+PubMed&email_add_text2=&EmailCheck1=&EmailCheck2=&coll_start2=1&citman_count2=20&citman_start2=1&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.EmailReport=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.EmailFormat=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.EmailCount=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.EmailStart=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.EmailSort=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.Email=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.EmailSubject=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.EmailText=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.EmailQueryKey=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.EmailHID=1JUaNZm7_muMenLr1UCg7qnKsykz3SEoWOFpZKTJpg1OPsm8DTZY4SFI2IPzWw7ap95YjxnHe5u1jGZfR_IvM4TVVA2azjhpkrl&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.QueryDescription=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.Key=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.Answer=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.Holding=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.HoldingFft=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.HoldingNdiSet=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.OToolValue=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.EmailTab.SubjectList=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.TimelineAdPlaceHolder.CurrTimelineYear=&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.TimelineAdPlaceHolder.BlobID=NCID_1_330998348_130.14.18.34_9001_1459126857_1489724809_0MetA0_S_MegaStore_F_1&EntrezSystem2.PEntrez.DbConnector.Db=pubmed&EntrezSystem2.PEntrez.DbConnector.LastDb=pubmed&EntrezSystem2.PEntrez.DbConnector.Term=bone+fracture&EntrezSystem2.PEntrez.DbConnector.LastTabCmd=&EntrezSystem2.PEntrez.DbConnector.LastQueryKey=1&EntrezSystem2.PEntrez.DbConnector.IdsFromResult=&EntrezSystem2.PEntrez.DbConnector.LastIdsFromResult=&EntrezSystem2.PEntrez.DbConnector.LinkName=&EntrezSystem2.PEntrez.DbConnector.LinkReadableName=&EntrezSystem2.PEntrez.DbConnector.LinkSrcDb=&EntrezSystem2.PEntrez.DbConnector.Cmd=PageChanged&EntrezSystem2.PEntrez.DbConnector.TabCmd=&EntrezSystem2.PEntrez.DbConnector.QueryKey=&p%24a=EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Entrez_Pager.Page&p%24l=EntrezSystem2&p%24st=pubmed&EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Entrez_Pager.CurrPage=1"
print(kw_url) r = requests.post(kw_url, headers=heads)
soup = BeautifulSoup(r.content.decode('gbk', 'ignore'))
#print(soup)
pagitation = soup.find('input', id="pageno")['last']
print('共有页面数:' + pagitation)

  

pubmed_cookie 自动获取的更多相关文章

  1. 转载-centos网络配置(手动设置,自动获取)的2种方法

    转载地址:http://blog.51yip.com/linux/1120.html 重新启动网络配置 # service network restart 或 # /etc/init.d/networ ...

  2. 分享一个快速设置背景的js 自动获取背景图的长宽

    我来分享一个快速设置背景的js (需要jq支持!) 快速切图铺页面用---就是不需要手动输入背景图的长宽 自动获取背景图的长宽 : <div class="wrap"> ...

  3. paip.enhes efis 自动获取文件的中文编码

    paip.enhes efis 自动获取文件的中文编码 ##为什么需要自动获取文件的中文编码 提高开发效率,自动获取文件的中文编码  .不需要手动设置编码...轻松的.. ##cpdetector 可 ...

  4. 关于启明星系统移除apppath配置,让系统自动获取路径来设置cookie的解决方法

    启明星系统底层使用统一接口,特别是用户,用户登录后,都会建立一个 userinfo 的cookie.请看下面2个网址: http://120.24.86.232/book http://120.24. ...

  5. ThinkPHP自动获取关键词(调用第三方插件)

    ThinkPHP自动获取关键词调用在线discuz词库 先按照下图路径放好插件 方法如下 /** * 自动获取关键词(调用第三方插件) * @return [type] [description] * ...

  6. 基于jquery的表格动态创建,自动绑定,自动获取值

    最近刚加入GUT项目,学习了很多其他同事写的代码,感觉受益匪浅. 在GUT项目中,经常会碰到这样一个问题:动态生成表格,包括从数据库中读取数据,并绑定在表格中,以及从在页面上通过jQuery新增删除表 ...

  7. I.MX6 Linux 自动获取AR1020 event input节点

    /*********************************************************************** * I.MX6 Linux 自动获取AR1020 ev ...

  8. ARM-Linux配置DHCP自动获取IP地址

    备注:内核版本:2.6.30.9busybox版本:1.15.2 PC Linux和开发板Linux的工作用户:root 1. 配置内核:[*] Networking support --->N ...

  9. Oracle VM Virtual 下CentOS不能自动获取IP地址

    在CentOS配置网卡开机自动获取IP地址: vi /etc/sysconfig/network-scripts/ifcfg-eth0 将 ONBOOT="no" 改为 ONBOO ...

随机推荐

  1. Rabbitmq vs. kafka

    https://mp.weixin.qq.com/s/2i_9TWoF3TsJvG6Dj_75vw http://www.cnblogs.com/valor-xh/p/6348009.html htt ...

  2. [cnblog新闻]历史性时刻:云硬件支出首次高于传统硬件

    https://news.cnblogs.com/n/617487/ 据调研公司 IDC 声称,2018 年第三季度云硬件支出占 IT 总收入的 50.9%. 知名调研公司 IDC 声称,面向云的 I ...

  3. 一个简单的修改 iis默认页面的方法..

    1. IIS 默认打开的是欢迎页面 2. 然后找到了一个比较简单的修改默认界面的方法: 找到这个文件的默认路径 C:\inetpub\wwwroot 然后修改 iisstart.htm 文件 在hea ...

  4. Oracle 的ORION工具简单使用

    1. 下载地址: http://www.oracle.com/technetwork/cn/topics/index-088165-zhs.html 2. linux x64 还有 windows的 ...

  5. ThreadPoolExecutor参数

    1.ThreadPoolExecutor个参数的意义(类上的注释内容) * @param corePoolSize the number of threads to keep in the* pool ...

  6. ubuntu更改分辨率

    1. 输入:$cvt 1920 1080 2 输入: $xrandr 3 输入: $sudo xrandr --newmode "1920x1080_60.00" 173.00 1 ...

  7. pip和conda到底有什么不一样?

    今天看到我的foreman开始报错去询问才发现.我们的python包管理工具已经从pip整体迁移到了conda..最近的迁移真的非常多..前端也在迁移打包

  8. OpenJS Foundation

    OpenJS Foundation Introducing the OpenJS Foundation https://openjsf.org/ The Node.js Foundation and ...

  9. html 列表 ol 、ul 、dl

    html的列表分為無序列表(ul).有序列表(ol).自定義列表(dl). 無序列表: 以<ul>開始,列表項以<li>開始: 列表項可以是段落.圖像.連接.換行符.列表等: ...

  10. Linux下创建和删除软、硬链接 可临时处理空间不足

    在Linux系统中,内核为每一个新创建的文件分配一个Inode(索引结点),每个文件都有一个惟一的inode号.文件属性保存在索引结点里,在访问文件时,索引结点被复制到内存在,从而实现文件的快速访问. ...