├── .gitignore ├── Config.conf ├── LICENSE ├── README.md ├── data_out.xls ├── result.png ├── spider_main.py ├── spider_paper.py └── spider_search_page.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | env/ 12 | build/ 13 | develop-eggs/ 14 | dist/ 15 | downloads/ 16 | eggs/ 17 | .eggs/ 18 | lib/ 19 | lib64/ 20 | parts/ 21 | sdist/ 22 | var/ 23 | *.egg-info/ 24 | .installed.cfg 25 | *.egg 26 | 27 | # PyInstaller 28 | # Usually these files are written by a python script from a template 29 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 30 | *.manifest 31 | *.spec 32 | 33 | # Installer logs 34 | pip-log.txt 35 | pip-delete-this-directory.txt 36 | 37 | # Unit test / coverage reports 38 | htmlcov/ 39 | .tox/ 40 | .coverage 41 | .coverage.* 42 | .cache 43 | nosetests.xml 44 | coverage.xml 45 | *,cover 46 | .hypothesis/ 47 | 48 | # Translations 49 | *.mo 50 | *.pot 51 | 52 | # Django stuff: 53 | *.log 54 | local_settings.py 55 | 56 | # Flask stuff: 57 | instance/ 58 | .webassets-cache 59 | 60 | # Scrapy stuff: 61 | .scrapy 62 | 63 | # Sphinx documentation 64 | docs/_build/ 65 | 66 | # PyBuilder 67 | target/ 68 | 69 | # IPython Notebook 70 | .ipynb_checkpoints 71 | 72 | # pyenv 73 | .python-version 74 | 75 | # celery beat schedule file 76 | celerybeat-schedule 77 | 78 | # dotenv 79 | .env 80 | 81 | # virtualenv 82 | venv/ 83 | ENV/ 84 | 85 | # Spyder project settings 86 | .spyderproject 87 | 88 | # Rope project settings 89 | .ropeproject 90 | -------------------------------------------------------------------------------- /Config.conf: -------------------------------------------------------------------------------- 1 | [base] 2 | keyword = 慢性粒细胞白血病 3 | currentpage = 70 4 | maxpage = 4784 5 | # 搜索模式，可以是全文、主题、篇名、作者、摘要 6 | searchlocation = 全文 7 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # CNKICrawler 2 | # 中国知网爬虫 3 | ## 可以爬取文章的全部信息,包括文章名、作者、作者单位、被引用次数、下载次数、文章来源、文章关键词、文章摘要、文章参考文献，文章详情页面url 4 | ## 需要安装的工具有：BeautifulSoup， xlwt 5 | 6 | ### 使用python3.x 7 | ### 运行spider_main.py即可，生成的结果文件为：data_out.xls，配置文件为Config.conf 8 | 9 | 运行结果： 10 | ![](result.png) 11 | 12 | 在线演示：http://www.qiuqingyu.cn/todolist/ 13 | 14 | 项目网址：http://www.qiuqingyu.cn/2017/04/27/python%E5%AE%9E%E7%8E%B0CNKI%E7%9F%A5%E7%BD%91%E7%88%AC%E8%99%AB/ 15 | -------------------------------------------------------------------------------- /data_out.xls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qiuqingyu/CNKICrawler/e676175576a93dda6481de9b2dc2ba53314c7d3f/data_out.xls -------------------------------------------------------------------------------- /result.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qiuqingyu/CNKICrawler/e676175576a93dda6481de9b2dc2ba53314c7d3f/result.png -------------------------------------------------------------------------------- /spider_main.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | from configparser import ConfigParser 3 | from urllib.parse import quote 4 | import socket 5 | import os 6 | import math 7 | import urllib.request 8 | from bs4 import BeautifulSoup 9 | import time 10 | import spider_search_page 11 | import spider_paper 12 | 13 | if __name__ == '__main__': 14 | start = time.clock() 15 | cf = ConfigParser() 16 | cf.read("Config.conf", encoding='utf-8') 17 | keyword = cf.get('base', 'keyword')# 关键词 18 | maxpage = cf.getint('base', 'maxpage')# 最大页码 19 | searchlocation = cf.get('base', 'searchlocation') #搜索位置 20 | currentpage = cf.getint('base', 'currentpage') 21 | if os.path.exists('data-detail.txt') and currentpage == 0: 22 | print('存在输出文件，删除该文件') 23 | os.remove('data-detail.txt') 24 | 25 | #构造不同条件的关键词搜索 26 | values = { 27 | '全文': 'qw', 28 | '主题': 'theme', 29 | '篇名': 'title', 30 | '作者': 'author', 31 | '摘要':'abstract' 32 | } 33 | keywordval = str(values[searchlocation])+':'+str(keyword) 34 | index_url='http://search.cnki.com.cn/Search.aspx?q='+quote(keywordval)+'&rank=&cluster=&val=&p='#quote方法把汉字转换为encodeuri? 35 | print(index_url) 36 | 37 | #获取最大页数 38 | html = urllib.request.urlopen(index_url).read() 39 | soup = BeautifulSoup(html, 'html.parser') 40 | pagesum_text = soup.find('span', class_='page-sum').get_text() 41 | maxpage = math.ceil(int(pagesum_text[7:-1]) / 15) 42 | #print(maxpage) 43 | cf = ConfigParser() 44 | cf.read("Config.conf", encoding='utf-8') 45 | cf.set('base', 'maxpage', str(maxpage)) 46 | cf.write(open('Config.conf', 'w', encoding='utf-8')) 47 | 48 | for i in range(currentpage, maxpage): 49 | page_num=15 50 | page_str_num=i*page_num 51 | page_url=index_url+str(page_str_num) 52 | print(page_url) 53 | attempts = 0 54 | success = False 55 | while attempts < 50 and not success: 56 | try: 57 | spider_search_page.get_paper_url(page_url) 58 | socket.setdefaulttimeout(10) # 设置10秒后连接超时 59 | success = True 60 | except socket.error: 61 | attempts += 1 62 | print("第"+str(attempts)+"次重试！！") 63 | if attempts == 50: 64 | break 65 | except urllib.error: 66 | attempts += 1 67 | print("第"+str(attempts)+"次重试！！") 68 | if attempts == 50: 69 | break 70 | cf.set('base', 'currentpage', str(i)) 71 | cf.write(open("Config.conf", "w", encoding='utf-8')) 72 | spider_paper.spider_paper()# spider_paper补全文章信息 73 | end = time.clock() 74 | print ('Running time: %s Seconds'%(end-start)) 75 | -------------------------------------------------------------------------------- /spider_paper.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | import socket 3 | 4 | from bs4 import BeautifulSoup 5 | import urllib 6 | import requests 7 | import time 8 | import xlwt 9 | from configparser import ConfigParser 10 | 11 | def spider_paper(): 12 | start = time.clock() 13 | # f=urllib2.urlopen(url, timeout=5).read() 14 | # soup=BeautifulSoup(html) 15 | # tags=soup.find_all('a') 16 | file = open("data-detail.txt", encoding='utf8') 17 | cf = ConfigParser() 18 | cf.read("Config.conf", encoding='utf-8') 19 | keyword = cf.get('base', 'keyword')# 关键词 20 | 21 | # 写入Excel 22 | wb = xlwt.Workbook("data_out.xls") 23 | sheet = wb.add_sheet("data-out") 24 | sheet.write(0, 0, '下载网址') 25 | sheet.write(0, 1, '标题') 26 | sheet.write(0, 2, '来源') 27 | sheet.write(0, 3, '引用') 28 | sheet.write(0, 4, '作者') 29 | sheet.write(0, 5, '作者单位') 30 | sheet.write(0, 6, '关键词') 31 | sheet.write(0, 7, '摘要') 32 | sheet.write(0, 8, '共引文献') 33 | 34 | lines = file.readlines() 35 | txt_num = 1 36 | lin_num = 1 37 | paper_list = [] 38 | for line in lines: 39 | object = line.split('\t') 40 | paper_url = object[0] 41 | if paper_url in paper_list: 42 | continue 43 | paper_list.append(paper_url) 44 | attempts = 0 45 | success = False 46 | while attempts < 50 and not success: 47 | try: 48 | html = urllib.request.urlopen(paper_url).read() 49 | soup = BeautifulSoup(html, 'html.parser') 50 | socket.setdefaulttimeout(10) # 设置10秒后连接超时 51 | success = True 52 | except socket.error: 53 | attempts += 1 54 | print("第"+str(attempts)+"次重试！！") 55 | if attempts == 50: 56 | break 57 | except urllib.error: 58 | attempts += 1 59 | print("第"+str(attempts)+"次重试！！") 60 | if attempts == 50: 61 | break 62 | title = soup.find_all('div', style="text-align:center; width:740px; font-size: 28px;color: #0000a0; font-weight:bold; font-family:'宋体';") 63 | abstract = soup.find_all('div', style='text-align:left;word-break:break-all') 64 | author = soup.find_all('div', style='text-align:center; width:740px; height:30px;') 65 | 66 | #获取作者名字 67 | for item in author: 68 | author = item.get_text() 69 | # print(item) 70 | #获取摘要信息 71 | tmp = '' 72 | for thing in abstract: 73 | a = thing.strings 74 | for string in a: 75 | tmp = tmp + string 76 | txt_num += 1 77 | result = tmp.split(' ') 78 | tstr = '' 79 | for t in result: 80 | test = t.split('\n') 81 | # print(test) 82 | if test != '\t' and test != '\n' and test != '\r' and test != '': 83 | for i in test: 84 | if len(i) > 1: 85 | item = i.split('\r') 86 | for j in item: 87 | object = j.split('\t') 88 | for k in object: 89 | tstr += k 90 | 91 | ifreferen = soup.find_all('td', class_='b14', rowspan='2') 92 | ref = '' 93 | for i in range(len(ifreferen)): 94 | if ('【共引文献】' in ifreferen[i].get_text()): 95 | referenceList = soup.find_all('div', id='div_Ref') # 共引文献列表 96 | if len(referenceList) == 0: 97 | referenceList = soup.find_all('div', class_='div_Ref') 98 | referenceList = referenceList[i] 99 | for tdref in referenceList.find_all('td', width='676'): 100 | refitem = tdref.a.get("href") 101 | refitem = refitem.strip() 102 | print(refitem) 103 | ref = ref + refitem + ' ,' 104 | # 获取作者单位，处理字符串匹配 105 | authorUnitScope = soup.find('div', style='text-align:left;', class_='xx_font') 106 | author_unit = '' 107 | author_unit_text = authorUnitScope.get_text() 108 | # print(author_unit_text) 109 | if '【作者单位】：' in author_unit_text: 110 | auindex = author_unit_text.find('【作者单位】：', 0) 111 | else: 112 | auindex = author_unit_text.find('【学位授予单位】：', 0) 113 | for k in range(auindex, len(author_unit_text)): 114 | if author_unit_text[k] == '\n' or author_unit_text[k] == '\t' or author_unit_text[k] == '\r' or \ 115 | author_unit_text[k] == '】': 116 | continue 117 | if author_unit_text[k] == ' ' and author_unit_text[k + 1] == ' ': 118 | continue 119 | if author_unit_text[k] != '【': 120 | author_unit = author_unit + author_unit_text[k] 121 | if author_unit_text[k] == '【' and k != auindex: 122 | break 123 | # 获取关键字 124 | key_word = '' 125 | kwindex = author_unit_text.find('【关键词】：', 0) 126 | for k in range(kwindex, len(author_unit_text)): 127 | if author_unit_text[k] == '\n' or author_unit_text[k] == '\t' or author_unit_text[k] == '\r' or \ 128 | author_unit_text[k] == '】': 129 | continue 130 | if author_unit_text[k] == ' ' and author_unit_text[k + 1] == ' ': 131 | continue 132 | if author_unit_text[k] != '【': 133 | key_word = key_word + author_unit_text[k] 134 | if author_unit_text[k] == '【' and k != kwindex: 135 | break 136 | # print(author_unit) 137 | # print(key_word) 138 | line = line.strip('\n') 139 | line = line + '\t' + str(author) + '\t' + str(author_unit) + '\t'+ str(key_word) + '\t'+ str(tstr) + '\t' + str(ref) + '\n' 140 | outstring = line.split('\t') 141 | for i in range(len(outstring)): 142 | sheet.write(lin_num, i, outstring[i]) 143 | print('写入第'+str(lin_num)+'行') 144 | lin_num += 1 145 | wb.save('data_out_'+str(keyword)+'.xls') 146 | 147 | file.close() 148 | end = time.clock() 149 | print('Running time: %s Seconds' % (end - start)) 150 | -------------------------------------------------------------------------------- /spider_search_page.py: -------------------------------------------------------------------------------- 1 | from bs4 import BeautifulSoup 2 | import urllib 3 | import urllib.request 4 | import sys 5 | import io 6 | 7 | sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding='utf8') 8 | 9 | page_num=15 10 | 11 | def get_paper_url(page_url): 12 | html = urllib.request.urlopen(page_url).read() 13 | soup = BeautifulSoup(html,'html.parser') 14 | 15 | f = open('data-detail.txt','a+', encoding='utf-8') 16 | all = soup.find_all('div', class_='wz_content') 17 | for string in all: 18 | item = string.find('a', target='_blank')#文章标题与链接 19 | href = item.get('href')# 获取文章url 20 | title = item.get_text() # 获取文章标题 21 | year_count = string.find('span', class_='year-count')#获取文章出处与引用次数 22 | #year_count = year_count.get_text() 23 | publish = '' 24 | reference = '' 25 | for item in year_count: 26 | item = item.string 27 | item = item.replace('\n','') 28 | item = item.replace('\r', '') 29 | if '被引次数' in item: 30 | reference = item# 获取被引次数 31 | elif '年' in item: # 获取文章出处 32 | publish = item 33 | #print(publish) 34 | #print(reference) 35 | #print(year_count) 36 | f.write(href + '\t' + title + '\t' + publish + '\t' + reference +'\n') 37 | f.close() 38 | --------------------------------------------------------------------------------