In f0nzie/petro.One: Statistics and Text Mining for Oil and Gas Papers from OnePetro Metadata
library(petro.One)
my_url <- make_search_url(query = "neural network",
how = "all"
)
get_papers_count(my_url)
# 3238
df <- papers_by_type(my_url)
df
# Conference paper 2881
# General 4
# Journal paper 323
# Media 2
# Other 5
# Presentation 23
sum(df$value)
# 3238
# specify document type = "conference-paper", rows = 1000
my_url <- make_search_url(query = "neural network",
how = "all",
dc_type = "conference-paper",
rows = 100)
get_papers_count(my_url)
papers_by_type(my_url)
df <- onepetro_page_to_dataframe(my_url)
df
my_url <- make_search_url(query = "neural network",
how = "all",
dc_type = "other",
rows = 100)
get_papers_count(my_url)
# 5
df <- onepetro_page_to_dataframe(my_url)
df
# Error in `[.data.frame`(source_data, , 5) : undefined columns selected
my_url <- make_search_url(query = "neural network",
how = "all",
dc_type = "media",
rows = 100)
get_papers_count(my_url)
# 2
df <- onepetro_page_to_dataframe(my_url)
df
# 0 rows
library(petro.One)
my_url <- make_search_url(query = "pressure"
)
get_papers_count(my_url)
# Search results: Your search for pressure has returned 132,327 results.
# 132327
papers_by_type(my_url)
# Chapter 87
# Conference paper 108985
# General 1521
# Journal paper 20807
# Media 107
# Other 158
# Presentation 559
# Standard 103
library(petro.One)
url <- make_search_url(query = "pressure",
rows = 90 # page of size 90
)
# get_papers_count(my_url)
df <- onepetro_page_to_dataframe(url)
df
# Error in onepetro_page_to_dataframe(my_url) : Dataframe sizes different
# WRB Lance Formation - Pressure Gradient
# Document Type: Other
get_papers_count(url)
webpage <- xml2::read_html(url)
petro.One:::read_titles(webpage)
petro.One:::read_sources(webpage)
petro.One:::read_author(webpage)
The question
How do we know the webpage we just read contains howmany of conference-paper, media or presentation kind of documents?
Is there a way to search the webpage for those tags?
Visit External Site
> read_html(url) %>%
+ html_nodes(., css = '.stats-container') %>%
+ html_text(url)
Error in xpath_class() :
could not find function "xpath_class"
>
>
> read_html(url) %>%
+ html_nodes(., xpath = '//*[contains(concat( " ", @class, " " ), concat( " ", "stats-container", " " ))]') %>%
+ html_text(url)
character(0)
wzxhzdk:34
wzxhzdk:35
wzxhzdk:36
wzxhzdk:37
wzxhzdk:38
wzxhzdk:39
wzxhzdk:40
wzxhzdk:41
wzxhzdk:42
The tag `result-link:nth-child(1)` returns a partial list of the papers. Some papers will not have download links.
wzxhzdk:43
wzxhzdk:44
## Represent a set of non-uniform sized dataframes in R
https://stackoverflow.com/questions/17125296/represent-a-set-of-non-uniform-sized-dataframes-in-r
wzxhzdk:45
data-type
dc_type-media
f0nzie/petro.One documentation built on May 29, 2019, 12:05 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.
library(petro.One) my_url <- make_search_url(query = "neural network", how = "all" ) get_papers_count(my_url) # 3238 df <- papers_by_type(my_url) df # Conference paper 2881 # General 4 # Journal paper 323 # Media 2 # Other 5 # Presentation 23 sum(df$value) # 3238
# specify document type = "conference-paper", rows = 1000 my_url <- make_search_url(query = "neural network", how = "all", dc_type = "conference-paper", rows = 100) get_papers_count(my_url) papers_by_type(my_url) df <- onepetro_page_to_dataframe(my_url) df
my_url <- make_search_url(query = "neural network", how = "all", dc_type = "other", rows = 100) get_papers_count(my_url) # 5 df <- onepetro_page_to_dataframe(my_url) df # Error in `[.data.frame`(source_data, , 5) : undefined columns selected
my_url <- make_search_url(query = "neural network", how = "all", dc_type = "media", rows = 100) get_papers_count(my_url) # 2 df <- onepetro_page_to_dataframe(my_url) df # 0 rows
library(petro.One) my_url <- make_search_url(query = "pressure" ) get_papers_count(my_url) # Search results: Your search for pressure has returned 132,327 results. # 132327 papers_by_type(my_url) # Chapter 87 # Conference paper 108985 # General 1521 # Journal paper 20807 # Media 107 # Other 158 # Presentation 559 # Standard 103
library(petro.One) url <- make_search_url(query = "pressure", rows = 90 # page of size 90 ) # get_papers_count(my_url) df <- onepetro_page_to_dataframe(url) df # Error in onepetro_page_to_dataframe(my_url) : Dataframe sizes different # WRB Lance Formation - Pressure Gradient # Document Type: Other
get_papers_count(url) webpage <- xml2::read_html(url) petro.One:::read_titles(webpage) petro.One:::read_sources(webpage) petro.One:::read_author(webpage)
The question
How do we know the webpage we just read contains howmany of conference-paper, media or presentation kind of documents?
Is there a way to search the webpage for those tags?
Visit External Site
> read_html(url) %>%
+ html_nodes(., css = '.stats-container') %>%
+ html_text(url)
Error in xpath_class() :
could not find function "xpath_class"
>
>
> read_html(url) %>%
+ html_nodes(., xpath = '//*[contains(concat( " ", @class, " " ), concat( " ", "stats-container", " " ))]') %>%
+ html_text(url)
character(0)
wzxhzdk:34
wzxhzdk:35
wzxhzdk:36
wzxhzdk:37
wzxhzdk:38
wzxhzdk:39
wzxhzdk:40
wzxhzdk:41
wzxhzdk:42
The tag `result-link:nth-child(1)` returns a partial list of the papers. Some papers will not have download links.
wzxhzdk:43
wzxhzdk:44
## Represent a set of non-uniform sized dataframes in R
https://stackoverflow.com/questions/17125296/represent-a-set-of-non-uniform-sized-dataframes-in-r
wzxhzdk:45
data-type
dc_type-media
f0nzie/petro.One documentation built on May 29, 2019, 12:05 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.