allatambov

import requests
from bs4 import BeautifulSoup

page = requests.get("http://nplus1.ru/")
soup = BeautifulSoup(page.text)

links_raw = soup.find_all("a")
links_all = []
for link in links_raw:
    links_all.append(link["href"])

allatambov

# !pip install selenium

from selenium import webdriver as wd
br = wd.Chrome("/Users/allat/Downloads/chromedriver")

br.get("http://www.biblio-globus.ru/")
search = br.find_element_by_id("search_string") 

search = br.find_element_by_id("search_string") 
search.send_keys("Python") 

allatambov

import requests
from bs4 import BeautifulSoup

page = requests.get("https://nplus1.ru/")
soup = BeautifulSoup(page.text)

raw_links = soup.find_all("a")
news = []

for link in raw_links:

allatambov

numbers = [1, 0, 3, -5, 9, -8, -10, -12, 3, 7, 8]


if numbers[0] > 0:
    print("Yes")
else:
    print("No")
    
if numbers[0] > 0:
    print("Yes")

allatambov

### installing and loading packages ###

install.packages("rvest")
library(rvest)
library(tidyverse)

### parsing HTML ###

# read HTML by link

allatambov

# dataset

View(USJudgeRatings)

# Pearson correlation

cor.test(USJudgeRatings$FAMI, USJudgeRatings$DECI)

# Spearman correlation

allatambov

get_news <- function(link1){
  page1 <- read_html(link1)
  page1 %>% html_nodes(".table")
  tables <- page1 %>% html_nodes(xpath = "//p[@class='table']")
  rubs <- tables[1] %>% html_nodes("a") %>% html_text()
  time <- tables[2] %>% html_nodes("time")
  date <- time %>% html_attr("content")
  date_unix <- time %>% html_attr("data-unix")
  time_human <- time %>% html_node("span") %>% html_text()
  diffc <- tables[3] %>% html_node(".difficult-value") %>% 

allatambov

# choose color

scat <- plot_ly(data = iris, x = ~Sepal.Length, y = ~Petal.Length,
                type = "scatter", mode = "markers", 
                marker = list(color = "blue"))

scat <- scat %>% layout(title = list(text = "<b>Iris Data</b>"),
                        updatemenus = list(list(x = -0.5,
                                           y = 4,
                                           buttons = list(

allatambov

## PART 1: PROPORTIONS ##

### COUNT DATA ###

girls <- read.csv("https://allatambov.github.io/twimc/names-girls.csv")
boys <- read.csv("https://allatambov.github.io/twimc/names-boys.csv")

girls <- girls[girls$Month == "январь" & girls$Year == 2018, ]

table(girls$Name)

allatambov

install.packages("tidyverse")
library(tidyverse)

anames <- read.csv("https://allatambov.github.io/twimc/names.csv", encoding = "UTF-8")

names18 <- anames %>% filter(Year == 2018 & Month == "январь")

names18_f <- names18 %>% filter(Sex == "female")
names18_m <- names18 %>% filter(Sex == "male")