Last active
April 3, 2020 11:15
-
-
Save isaurssaurav/7802cbcf37d65f338692f1f02e21c005 to your computer and use it in GitHub Desktop.
web_scrap
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# pip install requests | |
# pip install beautifulsoup4 | |
import requests | |
from bs4 import BeautifulSoup | |
def get_HTML_text(url): | |
response = requests.get(url) | |
## if any websites throw 403 add user agent and cookie | |
#use headers and send it as send argument in requests.get | |
#headers= { | |
#"user-agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36", | |
#"cookie": "__cfduid=de9fdff979531ae501164dc2c3e650e4d1568871390; _ga=GA1.2.870057641.1568871391; _fbp=fb.1.1568871391716.1151791623; __gads=ID=14242a785084d4d8:T=1568871391:S=ALNI_Mby30Q72TQcn9MggZXuhDXS-LC96w; PHPSESSID=42thds5b205itvgvliv5hicsv5; _gid=GA1.2.644164567.1585910282" | |
#} | |
#response = requests.get(url, headers=headers) | |
response_page = response.text | |
response_status = response.status_code | |
print(response_status) | |
if response_status == 200: | |
return response_page | |
elif response_status == 403: | |
raise Exception("try after minute again") | |
else: | |
raise Exception("oops something went wrong") | |
#get html txt of website | |
response_page = get_HTML_text("https://www.imdb.com/chart/boxoffice/?ref_=nv_ch_cht") | |
# parse html | |
response_page_soup = BeautifulSoup(response_page, "html.parser") | |
# select table | |
container = response_page_soup.find( | |
"table", {"class": "chart full-width"}) | |
# select table kok tbody ko tr | |
trs = container.find("tbody").findAll("tr") | |
# file open | |
try: | |
f = open("movies.csv", "w") | |
f.write("name, image \n") # headers | |
for tr in trs: | |
title = tr.find("td", {"class", "titleColumn"}).a.text | |
image = tr.find("td", {"class", "posterColumn"}).a.img["src"] | |
f.write(title+",\""+image+"\"\n") | |
except Exception as e: | |
print("oops", e) | |
else: | |
f.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment