- conda install -c anaconda beautifulsoup4
- pip install beautifulsoup4
from bs4 import BeautifulSoup
page = open("../data/03. zerobase.html", "r").read()
soup = BeautifulSoup(page, "html.parser")
print(soup.prettify())
# head 태그 확인
soup.head
# body 태그 확인
soup.body
# p 태그 확인
# 처음 발견한 p 태그만 출력
# find()
soup.p
soup.find("p")
soup.find("p", {"class":"inner-text first-item", "id":"first"}) # 다중 조건
# find_all(): 여러 개의 태그를 반환
# list 형태로 반환
soup.find_all("p")
# 특정 태그 확인
soup.find_all(id="pw-link")[0].text
soup.find_all("p", class_="innter-text second-item")
# 값만 출력
print(soup.find_all("p")[0].text)
print(soup.find_all("p")[1].string)
print(soup.find_all("p")[1].get_text())
# p 태그 리스트에서 텍스트 속성만 출력
for each_tag in soup.find_all("p"):
print("=" * 50)
print(each_tag.text)
# a 태그에서 href 속성값에 있는 값 추출
links = soup.find_all("a")
links[0].get("href"), links[1]["href"]
for each in links:
href = each.get("href") # each["href"]
text = each.get_text()
print(text + "=>" + href)
import requests
# from urllib.request.Request
from bs4 import BeautifulSoup
url = "https://finance.naver.com/marketindex/"
response = requests.get(url)
# requests.get(), requests.post()
# response.text
soup = BeautifulSoup(response.text, "html.parser")
print(soup.prettify())
# soup.find_all("li", "on")
# id => #
# class => .
exchangeList = soup.select("#exchangeList > li")
len(exchangeList), exchangeList
title = exchangeList[0].select_one(".h_lst").text
exchange = exchangeList[0].select_one(".value").text
change = exchangeList[0].select_one(".change").text
updown = exchangeList[0].select_one(".head_info.point_dn > .blind").text
# link
title, exchange, change, updown
baseUrl = "https://finance.naver.com"
baseUrl + exchangeList[0].select_one("a").get("href")
# 4개 데이터 수집
exchange_datas = []
baseUrl = "https://finance.naver.com"
for item in exchangeList:
data = {
"title": item.select_one(".h_lst").text,
"exchnage": item.select_one(".value").text,
"change": item.select_one(".change").text,
"updown": item.select_one(".head_info.point_dn > .blind").text,
"link": baseUrl + item.select_one("a").get("href")
}
exchange_datas.append(data)
df = pd.DataFrame(exchange_datas)
df.to_excel("./naverfinance.xlsx", encoding="utf-8")
import urllib
from urllib.request import urlopen, Request
html = "https://ko.wikipedia.org/wiki/{search_words}"
# https://ko.wikipedia.org/wiki/여명의_눈동자
req = Request(html.format(search_words=urllib.parse.quote("여명의_눈동자"))) # 글자를 URL로 인코딩
response = urlopen(req)
soup = BeautifulSoup(response, "html.parser")
print(soup.prettify())
n = 0
for each in soup.find_all("ul"):
print("=>" + str(n) + "========================")
print(each.get_text())
n += 1
soup.find_all("ul")[15].text.strip().replace("\xa0", "").replace("\n", "")
최종목표
총 51개 페이지에서 각 가게의 정보를 가져온다
- 가게이름
- 대표메뉴
- 대표메뉴의 가격
- 가게주소
# !pip install fake-useragent
from urllib.request import Request, urlopen
from fake_useragent import UserAgent
from bs4 import BeautifulSoup
url_base = "https://www.chicagomag.com/"
url_sub = "Chicago-Magazine/November-2012/Best-Sandwiches-Chicago/"
url = url_base + url_sub
ua = UserAgent()
req = Request(url, headers={"user-agent": ua.ie})
html = urlopen(req)
soup = BeautifulSoup(html, "html.parser")
print(soup.prettify())
soup.find_all("div", "sammy"), len(soup.find_all("div", "sammy"))
# soup.select(".sammy"), len(soup.select(".sammy"))
tmp_one= soup.find_all("div", "sammy")[0]
type(tmp_one)
tmp_one.find(class_="sammyRank").get_text()
# tmp_one.select_one(".sammyRank").text
tmp_one.find("div", {"class":"sammyListing"}).get_text()
# tmp_one.select_one(".sammyListing").text
tmp_one.find("a")["href"]
# tmp_one.select_one("a").get("href")
import re
tmp_string = tmp_one.find(class_="sammyListing").get_text()
re.split(("\n|\r\n"), tmp_string)
print(re.split(("\n|\r\n"), tmp_string)[0]) # menu
print(re.split(("\n|\r\n"), tmp_string)[1]) # cafe
from urllib.parse import urljoin
url_base = "http://www.chicagomag.com"
# 필요한 내용을 담을 빈 리스트
# 리스트로 하나씩 컬럼을 만들고, DataFrame으로 합칠 예정
rank = []
main_menu = []
cafe_name = []
url_add = []
list_soup = soup.find_all("div", "sammy") # soup.select(".sammy")
for item in list_soup:
rank.append(item.find(class_="sammyRank").get_text())
tmp_string = item.find(class_="sammyListing").get_text()
main_menu.append(re.split(("\n|\r\n"), tmp_string)[0])
cafe_name.append(re.split(("\n|\r\n"), tmp_string)[1])
url_add.append(urljoin(url_base, item.find("a")["href"]))
import pandas as pd
data = {
"Rank": rank,
"Menu": main_menu,
"Cafe": cafe_name,
"URL": url_add,
}
df = pd.DataFrame(data)
# 컬럼 순서 변경
df = pd.DataFrame(data, columns=["Rank", "Cafe", "Menu", "URL"])
df.tail()
# 데이터 저장
df.to_csv(
"../data/03. best_sandwiches_list_chicago.csv", sep=",", encoding="utf-8"
)
# requirements
import pandas as pd
from urllib.request import urlopen, Request
from fake_useragent import UserAgent
from bs4 import BeautifulSoup
df = pd.read_csv("../data/03. best_sandwiches_list_chicago.csv", index_col=0)
df["URL"][0]
req = Request(df["URL"][0], headers={"user-agent":ua.ie})
html = urlopen(req).read()
soup_tmp = BeautifulSoup(html, "html.parser")
soup_tmp.find("p", "addy") # soup_find.select_one(".addy")
# regular expression
price_tmp = soup_tmp.find("p", "addy").text
price_tmp
import re
re.split(".,", price_tmp)
price_tmp = re.split(".,", price_tmp)[0]
price_tmp
tmp = re.search("\$\d+\.(\d+)?", price_tmp).group()
price_tmp[len(tmp) + 2:]
from tqdm import tqdm
price = []
address = []
for idx, row in tqdm(df[:5].iterrows()):
req = Request(row["URL"], headers={"user-agent":ua.ie})
html = urlopen(req).read()
soup_tmp = BeautifulSoup(html, "html.parser")
gettings = soup_tmp.find("p", "addy").get_text()
price_tmp = re.split(".,", gettings)[0]
tmp = re.search("\$\d+\.(\d+)?", price_tmp).group()
price.append(tmp)
address.append(price_tmp[len(tmp)+2:])
print(idx)
df.tail(2)
df["Price"] = price
df["Address"] = address
df = df.loc[:, ["Rank", "Cafe", "Menu", "Price", "Address"]]
df.set_index("Rank", inplace=True)
df.head()
# requirements
import folium
import pandas as pd
import numpy as np
import googlemaps
from tqdm import tqdm
df = pd.read_csv("../data/03. best_sandwiches_list_chicago2.csv", index_col=0)
df.tail(10)
gmaps_key = ""
gmaps = googlemaps.Client(key=gmaps_key)
lat = []
lng = []
for idx, row in tqdm(df.iterrows()):
if not row["Address"] == "Multiple location":
target_name = row["Address"] + ", " + "Chicago"
# print(target_name)
gmaps_output = gmaps.geocode(target_name)
location_ouput = gmaps_output[0].get("geometry")
lat.append(location_ouput["location"]["lat"])
lng.append(location_ouput["location"]["lng"])
# location_output = gmaps_output[0]
else:
lat.append(np.nan)
lng.append(np.nan)
df["lat"] = lat
df["lng"] = lng
df.tail()
mapping = folium.Map(location=[41.8781136, -87.6297982], zoom_start=11)
for idx, row in df.iterrows():
if not row["Address"] == "Multiple location":
folium.Marker(
location=[row["lat"], row["lng"]],
popup=row["Cafe"],
tooltip=row["Menu"],
icon=folium.Icon(
icon="coffee",
prefix="fa"
)
).add_to(mapping)
mapping
데이터 수집을 자동화하는 BeautifulSoup. Html을 배웠던 것이 약간은 유용한 듯 하다. 어쨌거나 데이터 구조를 파악하고 원하는 데이터를 추출하는 코딩 역량도 필수로 가져야겠다.