From 2c327a733d8c115e93e0d2269a2a65bdaabc2ba8 Mon Sep 17 00:00:00 2001 From: Gbanyan Date: Fri, 10 Aug 2018 21:11:35 +0800 Subject: [PATCH] Found Uptodate API and apply with requests --- Main.py | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/Main.py b/Main.py index 71a7d98..f9d86e0 100644 --- a/Main.py +++ b/Main.py @@ -6,8 +6,10 @@ import html5lib import re import sys - +#Def the Uptodate URI for use up_search_url = "https://www.uptodate.com/contents/search?search=" +up_api_url = "https://www.uptodate.com/services/app/contents/search/2/json?&language=en&max=10&search=" +up_prefix_url = "https://www.uptodate.com" def do_uptodate_search_with_gecko(key_word): print(up_search_url + key_word) @@ -19,18 +21,21 @@ def do_uptodate_search_with_gecko(key_word): for links in articles_links: print(links) -def do_uptodate_search(key_word): +def do_uptodate_search_with_headless(key_word): print(up_search_url + key_word) - driver = webdriver.Firefox() + option = webdriver.ChromeOptions() + option.add_argument('headless') + driver = webdriver.Chrome(chrome_options=option) driver.get(up_search_url + key_word) html = driver.page_source soup = BeautifulSoup(html, 'html.parser') - print(html) - articles_links = soup.find_all("div.search-result") + articles_links = soup.select("#search-results-container") + print(articles_links) - for link in articles_links: - print(link) +def do_uptodate_search_with_uptodate_api(key_word): + search_results = requests.get(up_api_url + key_word) + print(search_results.json()) if __name__ == '__main__': key_word = input("Please enter your keyword: ") - do_uptodate_search_with_gecko(key_word) + do_uptodate_search_with_uptodate_api(key_word)