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. Spring使用Cache、整合Ehcache(转)

    今天在做Spring使用Cache.整合Ehcache时发现一篇非常好的文章,原文地址 http://elim.iteye.com/blog/2123030 从3.1开始,Spring引入了对Cach ...

  2. vuex的数据交互

    methods:{ ...mapMutations({aaa:hs}) //将mutations的方法暴露出来,进行调用 aaa是他的名字 ...mapActions(['hs']) //将actio ...

  3. [读书笔记]SQLSERVER企业级平台管理实践读书笔记02

    记录一下 这一块 join的理解了 再完善过来. 1. Statistics的用法: 清空执行计划用的命令 dbcc freeproccache 清空buffer pool 里面的缓存命令 dbcc ...

  4. js控制浏览器全屏

    HTML 5中的full screen,目前可以在除IE和opera外的浏览器中使用 ,有的时候用来做全屏API,游戏呀,等都很有用.先看常见的API element.requestFullScree ...

  5. python模块_hashlib详解

    hashlib 摘要算法简介 Python的hashlib提供了常见的摘要算法,如MD5,SHA1等等. 什么是摘要算法呢?摘要算法又称哈希算法.散列算法.它通过一个函数,把任意长度的数据转换为一个长 ...

  6. flask+mako+peewee(上)

    其实关于什么用flask搭建一个后台博客啥的跟着官方文档做一遍就行了.感觉啥都有我这里就不赘述了只是记录一个笔记,因为稍微有几个地方有点坑. 目标:做了一个简易页面给电商的同事用来添加商品 首先是安装 ...

  7. p3c安装使用 编码规范扫描 阿里巴巴出品,挺好用的

    https://github.com/alibaba/p3c/wiki/IDEA%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8%E6%96%87%E6%A1%A3

  8. CF-Contest339-614

    614A-Link/Cut Tree 比较水,注意64位int仍然可能溢出. #include <cstdio> #include <algorithm> #include & ...

  9. POI 生成excel(大数据量) SXSSF

    使用POI 的SXSSF (Streaming Usermodel API)生成较大的excel,同时开启压缩 import junit.framework.Assert; import org.ap ...

  10. CUBA在查询语句如何添加参数

    在browse.xml中的collectionDatasource 可以添加查询语句,使用 “= :custom$param”  的形式 <collectionDatasource id=&qu ...