首页 技术 正文
技术 2022年11月19日
0 收藏 755 点赞 4,776 浏览 7007 个字

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)

  

相关推荐
python开发_常用的python模块及安装方法
adodb:我们领导推荐的数据库连接组件bsddb3:BerkeleyDB的连接组件Cheetah-1.0:我比较喜欢这个版本的cheeta…
日期:2022-11-24 点赞:878 阅读:8,985
Educational Codeforces Round 11 C. Hard Process 二分
C. Hard Process题目连接:http://www.codeforces.com/contest/660/problem/CDes…
日期:2022-11-24 点赞:807 阅读:5,501
下载Ubuntn 17.04 内核源代码
zengkefu@server1:/usr/src$ uname -aLinux server1 4.10.0-19-generic #21…
日期:2022-11-24 点赞:569 阅读:6,345
可用Active Desktop Calendar V7.86 注册码序列号
可用Active Desktop Calendar V7.86 注册码序列号Name: www.greendown.cn Code: &nb…
日期:2022-11-24 点赞:733 阅读:6,128
Android调用系统相机、自定义相机、处理大图片
Android调用系统相机和自定义相机实例本博文主要是介绍了android上使用相机进行拍照并显示的两种方式,并且由于涉及到要把拍到的照片显…
日期:2022-11-24 点赞:512 阅读:7,763
Struts的使用
一、Struts2的获取  Struts的官方网站为:http://struts.apache.org/  下载完Struts2的jar包,…
日期:2022-11-24 点赞:671 阅读:4,839