Created
January 23, 2018 06:40
-
-
Save dheepakg/5d25cceb34c62344b985a154903d606e to your computer and use it in GitHub Desktop.
wikiScrap
This file contains hidden or 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
| from bs4 import BeautifulSoup | |
| import requests | |
| #beautifulSoup('AR_Rahman.html',"html_parser") | |
| #print(soup.Title) | |
| #url = 'https://en.wikipedia.org/wiki/A._R._Rahman' | |
| url = 'https://en.wikipedia.org/wiki/Bombay_(soundtrack)' | |
| #url = 'https://assets.digitalocean.com/articles/eng_python/beautiful-soup/mockturtle.html' | |
| page = requests.get(url) | |
| print(page.status_code) | |
| soup = BeautifulSoup(page.text,"html.parser") | |
| html_file = open('AR_Rahman.html','w') | |
| html_file.write(soup.prettify()) | |
| #print(soup.find_all('p')) | |
| table_list = soup.find_all('td') | |
| #print("here 11\n",len(table_list),type(table_list)) | |
| song_list = soup.findAll('td', style="vertical-align:top") | |
| #print("here 22\n",len(song_list),type(song_list)) | |
| for row_num,element in enumerate(song_list): | |
| print("row_num",row_num,"first if",element) | |
| if row_num:# in (10,11) : | |
| print("row_num",row_num,"second if", element) | |
| element_list = list(element) | |
| if str(element_list)[4]+str(element_list)[5]+str(element_list)[6]+ str(element_list)[7] != 'href': | |
| print("row_num",row_num,"third if", element) | |
| abc = list(element_list)[0] | |
| if abc[0] == '"': | |
| print("row_num",row_num,"4th if", element) | |
| print("row_num",row_num,"Song with quotes", abc) |
This file contains hidden or 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
| from bs4 import BeautifulSoup | |
| import requests | |
| #beautifulSoup('AR_Rahman.html',"html_parser") | |
| #print(soup.Title) | |
| #url = 'https://en.wikipedia.org/wiki/Python_(programming_language)' | |
| #url = 'https://www.digitalocean.com/community/tutorials/how-to-scrape-web-pages-with-beautiful-soup-and-python-3' | |
| url = 'https://assets.digitalocean.com/articles/eng_python/beautiful-soup/mockturtle.html' | |
| page = requests.get(url) | |
| print(page.status_code) | |
| soup = BeautifulSoup(page.text,"html.parser") | |
| print(soup.find_all('p')) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment