Python爬虫抓取论文引用量

Python爬虫抓取论文引用量

1 平台情况介绍

ACM(Association for Computing Machinery)指美国计算机协会,是全球历史最悠久和最大的计算机教育和科研机构.ACM数据库收录了大量关于信息技术教育、科研和应用方面的期刊和会议论文,是计算机和信息技术领域十分重要的资源窗口.
但是该平台在检索方面存在一定的问题，如以“Trajectory data”为主题检索2019-2021年的期刊论文，当以被引量排序时，排在前列的往往是高引用、低相关的论文，而这与我们的检索初衷相违背。

2 爬虫抓取引用量

一种替代方法是先按相关度排序，再对相关度前100的论文取被引量较高的文献。这样既可以保证高引用，又可以确保高相关。
通过Python爬虫可以快速批量抓取按相关度排名时各论文的被引量，首先拿下网页的源码，然后通过Python正则表达式匹配，找出论文标题、作者、被引量等信息即可。
类似的思路同样适用于Springer等平台，但正则表达式需要修改，且循环获取数据时需要考虑被引量是否直接显示在了检索界面上。若未显示，则需要模拟浏览器进入论文详情界面获取。

2.1 正则表达式匹配

匹配实质上就是从html文件中找到信息出现的位置，通常这些信息前后会有固定的格式，从而可以实现匹配。

//匹配论文链接
findlink = re.compile(r'
')
//匹配论文标题
findtitle = re.compile(r'(.*?)')
//匹配论文被引量
findcitation = re.compile(r'.*?(.*?)')
//匹配论文作者
findauthor = re.compile(r'')

2.2 循环获取数据

def getData():
	//可以将网页代码保存到本地，也可以通过askURL()获取
    # html = askURL("https://dlnext.acm.org/action/doSearch?fillQuickSearch=false&target=advanced&expand=dl&field1=AllField&text1=Trajectory+Data+&AfterYear=2019&BeforeYear=2021&startPage=0&pageSize=50")
    html = open("ACMTop100.html", 'r', encoding='utf-8')
    //网页解析器
    soup = BeautifulSoup(html, 'html.parser')
    # print(soup)
    //对于每一条论文信息
    for item in soup.find_all(attrs={'class':'search__item issue-item-container'}):
        item = str(item)
        //正则表达式匹配
        link = re.findall(findlink, item)[0]
        link = "https://dlnext.acm.org" + link
        title = re.findall(findtitle, item)
        //信息缺失特殊处理
        if len(title) > 0:
            title = title[0]
            title = str(title)
            title = title.replace('','')
            title = title.replace('','')
        citation = re.findall(findcitation, item)[0]
        author = re.findall(findauthor, item)
        # print(link)
        # print(title)
        # print(citation)
        # print(author)
        //保存数据
        data = [link, title, citation, author]
        datalist.append(data)

2.3 数据保存

def saveData(datalist, savepath):
    print("save...")
    book = xlwt.Workbook(encoding='utf-8', style_compression=0)
    sheet = book.add_sheet("ACMTop100", cell_overwrite_ok=True)
    //列名
    col = ("link", "title", "citation", "author")
    for i in range(0, 4):
        sheet.write(0, i, col[i])
    //相关度前100项记录
    for i in range(0, 100):
        if i % 9 == 0:
            print("---------第{}条-----------".format(i+1))
        data = datalist[i]
        for j in range(0, 4):
            sheet.write(i + 1, j, data[j])
    book.save(savepath)

3 完整代码

process.py

import re
from bs4 import BeautifulSoup
import urllib.request
import xlwt

findlink = re.compile(r'
')
findtitle = re.compile(r'(.*?)')
findcitation = re.compile(r'.*?(.*?)')
findauthor = re.compile(r'')

datalist = []
def askURL(URL):
    head = {"user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36 Edg/94.0.992.38"}
    request = urllib.request.Request(URL,headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
        #print(html)
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)
    return html


def getData():
    # html = askURL("https://dlnext.acm.org/action/doSearch?fillQuickSearch=false&target=advanced&expand=dl&field1=AllField&text1=Trajectory+Data+&AfterYear=2019&BeforeYear=2021&startPage=0&pageSize=50")
    html = open("ACMTop100.html", 'r', encoding='utf-8')
    soup = BeautifulSoup(html, 'html.parser')
    # print(soup)
    for item in soup.find_all(attrs={'class':'search__item issue-item-container'}):
        item = str(item)
        link = re.findall(findlink, item)[0]
        link = "https://dlnext.acm.org" + link
        title = re.findall(findtitle, item)
        if len(title) > 0:
            title = title[0]
            title = str(title)
            title = title.replace('','')
            title = title.replace('','')
        citation = re.findall(findcitation, item)[0]
        author = re.findall(findauthor, item)
        print(link)
        print(title)
        print(citation)
        print(author)
        data = [link, title, citation, author]
        datalist.append(data)

def saveData(datalist, savepath):
    print("save...")
    book = xlwt.Workbook(encoding='utf-8', style_compression=0)
    sheet = book.add_sheet("ACMTop100", cell_overwrite_ok=True)
    col = ("link", "title", "citation", "author")
    for i in range(0, 4):
        sheet.write(0, i, col[i])
    for i in range(0, 100):
        if i % 9 == 0:
            print("---------第{}条-----------".format(i+1))
        data = datalist[i]
        for j in range(0, 4):
            sheet.write(i + 1, j, data[j])

    book.save(savepath)

if __name__ == "__main__":
    getData()
    saveData(datalist,"ACMPaperTop100.xls")

本文所用ACM网页源码html
本文爬取结果xls