pubchunks：提取学术文章的某部分
背景
pubchunks 的目的是从XML格式的学术文章中获取部分数据。我们不需要了解XML及其所有的格式原理。只需知道我们的文件或XML字符串在哪里以及我们想要每篇文章的哪些部分。然后用户可以组合这些部分并做我们希望下游的任何事情; 例如,分析文本结构
pubchunks中的函数
两个主要功能是：
- pub_chunks()：获取XML部分
- pub_tabularize()：强制输出pub_chunks()到data.frame中
- pub_guess_publisher()：从XML文件或字符串猜测发布者
- pub_sections()：部分pubchunks知道如何处理
- pub_providers()：提供者（即发布者）pubchunks知道如何明确处理
支持的出版商
- elife
- plos
- elsevier
- hindawi
- pensoft
- peerj
- copernicus
- frontiers
- f1000research
支持提取的部分有:
- Front - 发布者，期刊和文章元数据元素
- Body - 文章的正文
- Back - 文章的背面，致谢，作者贡献，参考文献
- Title - 文章标题
- Doi - 文章doi
- Categories - 发布商的类别，如果有的话
- Author - 作者
- Aff - 隶属关系（包括作者姓名）
- Keyword - 关键字
- Abstract - 文章摘要
- Executive_summary - 文章执行摘要
- Refs - 参考文献
- Refs_dois - 参考dois - 如果有的话
- Publisher - 发布者名称
- Journal_meta - 期刊元数据
- Article_meta - 文章元数据
- Acknowledgments - 致谢
- Permissions - 文章权限
- History - 日期，收到，出版，接受等
安装
#install.packages("pubchunks")
#
#remotes::install_github("ropensci/pubchunks")
#
#remotes::install_github("ropensci/pubchunks@fix-pub_chunks")
library(pubchunks)Import
- XML Path(s)
#path
path <- system.file("examples/pensoft_1.xml", package = "pubchunks")
#paths
pensoft_xml <- system.file("examples/pensoft_1.xml", package = "pubchunks")
peerj_xml <- system.file("examples/peerj_1.xml", package = "pubchunks")
copernicus_xml <- system.file("examples/copernicus_1.xml", package = "pubchunks")
frontiers_xml <- system.file("examples/frontiers_1.xml", package = "pubchunks")
paths <- list(pensoft_xml, peerj_xml, copernicus_xml, frontiers_xml)
pub_chunks(
paths,
sections = c("abstract", "title", "authors", "refs")
)## [[1]]
## <pub chunks>
## from: character
## sections: abstract, title, authors, refs
## abstract (n=1): AbstractNineteen species of seed-beetles belonging ...
## title (n=1): Contribution to the knowledge of seed-beetles (Col ...
## authors (n=7): nested list
## refs (n=13): AntonKW (2010) Catalogue of Palaearctic Coleoptera
##
## [[2]]
## <pub chunks>
## from: character
## sections: abstract, title, authors, refs
## abstract (n=1): Climate change is predicted to lead to more extrem ...
## title (n=1): Storm effects on intertidal invertebrates: increas ...
## authors (n=7): nested list
## refs (n=60): Alcántara-Carrió et al. (2017)Alcántara-CarrióJSas
##
## [[3]]
## <pub chunks>
## from: character
## sections: abstract, title, authors, refs
## abstract (n=1): Soil temperatures at various depths are unique par ...
## title (n=1): Quality control of 10-min soil temperatures data a ...
## authors (n=3): nested list
## refs (n=9): 1Bertrand, C., Gonzalez Sotelino, L., and Journée,
##
## [[4]]
## <pub chunks>
## from: character
## sections: abstract, title, authors, refs
## abstract (n=1): Our current understanding of Antarctic soils is de ...
## title (n=1): Metagenomic Analysis of a Southern Maritime Antarc ...
## authors (n=8): nested list
## refs (n=56): AislabieJ.BroadyP.SaulD. (2006). Culturable hetero
##
## attr(,"ft_data")
## [1] FALSEx <- path
pub_chunks(x, sections = "abstract")## <pub chunks>
## from: character
## sections: abstract
## abstract (n=1): AbstractNineteen species of seed-beetles belonging ...pub_chunks(x, sections = "aff")## <pub chunks>
## from: character
## sections: aff
## aff (n=7): nested listpub_chunks(x, sections = c("abstract", "title", "authors", "refs"))## <pub chunks>
## from: character
## sections: abstract, title, authors, refs
## abstract (n=1): AbstractNineteen species of seed-beetles belonging ...
## title (n=1): Contribution to the knowledge of seed-beetles (Col ...
## authors (n=7): nested list
## refs (n=13): AntonKW (2010) Catalogue of Palaearctic Coleoptera- Strings
xml_str <- paste0(readLines(path), collapse = "\n")
pub_chunks(xml_str, sections = "title")## <pub chunks>
## from: character
## sections: title
## title (n=1): Contribution to the knowledge of seed-beetles (Col ...- xml_document
xml_doc <- xml2::read_xml(path)
class(xml_doc)## [1] "xml_document" "xml_node"pub_chunks(xml_doc, sections = "title")## <pub chunks>
## from: xml_document
## sections: title
## title (n=1): Contribution to the knowledge of seed-beetles (Col ...- Doi
library("fulltext")
dois <- c('10.1371/journal.pone.0086169', '10.1371/journal.pone.0155491',
'10.7554/eLife.03032')
x <- fulltext::ft_get(dois) %>% fulltext::ft_collect()
pub_chunks(x, sections="authors")## $plos
## $plos$`10.1371/journal.pone.0086169`
## <pub chunks>
## from: xml_document
## sections: authors
## authors (n=4): nested list
##
## $plos$`10.1371/journal.pone.0155491`
## <pub chunks>
## from: xml_document
## sections: authors
## authors (n=9): nested list
##
##
## $elife
## $elife$`10.7554/eLife.03032`
## <pub chunks>
## from: xml_document
## sections: authors
## authors (n=6): nested list
##
##
## attr(,"ft_data")
## [1] TRUEOutput
List: default
Dataframe: 输出表格
path <- system.file("examples/elife_1.xml", package = "pubchunks")
res <- pub_chunks(x, c("doi", "title", "keywords"))
pub_tabularize(res)## $plos
## $plos$`10.1371/journal.pone.0086169`
## doi
## 1 10.1371/journal.pone.0086169
## title
## 1 Holsteins Favor Heifers, Not Bulls: Biased Milk Production Programmed during Pregnancy as a Function of Fetal Sex
## .publisher
## 1 plos
##
## $plos$`10.1371/journal.pone.0155491`
## doi
## 1 10.1371/journal.pone.0155491
## title
## 1 Uterine Expression of NDRG4 Is Induced by Estrogen and Up-Regulated during Embryo Implantation Process in Mice
## .publisher
## 1 plos
##
##
## $elife
## $elife$`10.7554/eLife.03032`
## doi title
## 1 10.7554/eLife.03032 MicroRNA-mediated repression of nonsense mRNAs
## 2 10.7554/eLife.03032 MicroRNA-mediated repression of nonsense mRNAs
## 3 10.7554/eLife.03032 MicroRNA-mediated repression of nonsense mRNAs
## 4 10.7554/eLife.03032 MicroRNA-mediated repression of nonsense mRNAs
## 5 10.7554/eLife.03032 MicroRNA-mediated repression of nonsense mRNAs
## 6 10.7554/eLife.03032 MicroRNA-mediated repression of nonsense mRNAs
## keywords .publisher
## 1 microRNA elife
## 2 nonsense mutation elife
## 3 nonsense-mediated mRNA decay elife
## 4 APC elife
## 5 intron retention elife
## 6 premature termination codon elife#paths
paths <- list(pensoft_xml, peerj_xml, copernicus_xml, frontiers_xml)
out <- pub_chunks(
paths,
sections = c("doi", "title", "keywords")
)
pub_tabularize(out)## [[1]]
## title
## 1 Contribution to the knowledge of seed-beetles (Coleoptera, Chrysomelidae, Bruchinae) in Xinjiang, China
## .publisher
## 1 pensoft
##
## [[2]]
## title
## 1 Storm effects on intertidal invertebrates: increased beta diversity of few individuals and species
## .publisher
## 1 peerj
##
## [[3]]
## doi
## 1 10.5194/asr-12-23-2015
## title .publisher
## 1 Quality control of 10-min soil temperatures data at RMI copernicus
##
## [[4]]
## doi
## 1 10.3389/fmicb.2012.00403
## title .publisher
## 1 Metagenomic Analysis of a Southern Maritime Antarctic Soil frontiers#rbind a list of dataframe
data.table::rbindlist(pub_tabularize(out), fill = TRUE)## title
## 1: Contribution to the knowledge of seed-beetles (Coleoptera, Chrysomelidae, Bruchinae) in Xinjiang, China
## 2: Storm effects on intertidal invertebrates: increased beta diversity of few individuals and species
## 3: Quality control of 10-min soil temperatures data at RMI
## 4: Metagenomic Analysis of a Southern Maritime Antarctic Soil
## .publisher doi
## 1: pensoft <NA>
## 2: peerj <NA>
## 3: copernicus 10.5194/asr-12-23-2015
## 4: frontiers 10.3389/fmicb.2012.00403