Doraemon 0.3

A toolkit of Doraemon

Doraemon is a toolkit including frequently used code. It is still in development...

Installation

pip install Doraemon

Checklist

1. Google Knowledge Graph
2. Google Translator
3. Robust Requests
4. User-friendly Chrome

Example

##1. Google Knowledge Graph

from Doraemon.OnlineSearch import google_KG

def get_proxies():
    proxy_str = "127.0.0.1:1080"
    proxies = {"http": "http://%s" % proxy_str,
               "https": "http://%s" % proxy_str, }
    return proxies

res = google_KG.get_entity("alibaba", get_proxies_fun=get_proxies)
print(res)

##2. Google Translator

from Doraemon.OnlineSearch import google_translator

def get_proxies():
    proxy_str = "127.0.0.1:1080"
    proxies = {"http": "http://%s" % proxy_str,
               "https": "http://%s" % proxy_str, }
    return proxies

ori_text = "中华民国"
res1 = google_translator.trans(ori_text, tl="zh-TW", get_proxies_fun=get_proxies)
long_text = ori_text * 2500 
res2 = google_translator.trans_long(long_text, )# if len(text) > 5000

print(res1)
print(res2)

##3. Robust Requests

from Doraemon.Requests import requests_dora
url = "https://www.baidu.com"

headers = requests_dora.get_default_headers()
headers["User-Agent"] = requests_dora.get_random_user_agent()

def get_proxies():
    proxy_str = "127.0.0.1:1080"
    proxies = {"http": "http://%s" % proxy_str,
               "https": "http://%s" % proxy_str, }
    return proxies

# max_times, get_proxies_fun, and invoked_by is optional, other parameters are the same as the requests.get() and requests.post()
res1 = requests_dora.try_best_2_get(url, max_times=5, get_proxies_fun=get_proxies, invoked_by="parent_fun_name") 
res2 = requests_dora.try_best_2_post(url, max_times=5, get_proxies_fun=get_proxies)
print(res1.status_code)
print(res2.status_code)

##4. User-friendly Chrome

from Doraemon.Requests import chrome_dora

proxy = "127.0.0.1:1080"
baidu_url = "https://www.baidu.com"
# no_images: do not load images(response more quickly)
# headless: make the chrome invisible
# proxy: set if you need
# they are all optional
chrome = chrome_dora.MyChrome(headless=False, proxy="127.0.0.1:1080", no_images=True) 
chrome.get(baidu_url)
print(chrome.page_source)