def __init__(self, politician_name):
"""Initialize an object representing an article."""
news = GoogleNews()
news.setlang("uk")
news.setencode("utf-8")
news.setperiod("3d")
news.search(politician_name)
info = news.result()
self.articles = []
name, surname = politician_name.split()[0], politician_name.split()[1]
self.link = f"https://www.google.com/search?q=+{name}+{surname}+новини&source=lnms&tbm=isch"
def get_data(self):
r = requests.get(self.link)
return r.text
html_data = get_data(self)
soup = BeautifulSoup(html_data, "html.parser")
image_links, num = [], 0
for item in soup.find_all("img"):
image_links.append(item["src"])
num += 1
if num == 6:
break
for i in range(5):
text = info[i]
info_list = [text["title"], text["link"], image_links[i + 1]]
self.articles.append(info_list)
def initalize_google_news(start_date, end_date):
"""Initializes the googlenews object."""
print("initalize_google_news...")
googlenews = GoogleNews(encode="utf-8") # create googlenews object
googlenews.setlang("en")
googlenews.setperiod("d")
googlenews.setencode("utf-8")
googlenews.setTimeRange(start_date, end_date) # using user specified date range
return googlenews
class Engine:
def __init__(self):
self.news = GoogleNews()
self.news.setlang('en')
#self.news.setTimeRange('01/01/2000','01/01/2015')
self.news.setencode('utf-8')
self.pageNumber = 1
self.searchTerm = ""
def nextPage(self):
if self.news.result == None:
raise RuntimeError("Engine has not searched yet")
self.pageNumber += 1
self.news.clear()
self.news.getpage(self.pageNumber)
if len(self.news.result()) == 0: return False
else: return True
def previousPage(self):
if self.news.result == None:
raise RuntimeError("Engine has not searched yet")
self.pageNumber -= 1
self.news.clear()
self.news.getpage(self.pageNumber)
if len(self.news.result()) == 0: return False
else: return True
def search(self, term):
self.news.search(term)
if len(self.news.result()) == 0:
return False
else:
return self.news.result()
def getPageNumber(self):
return self.pageNumber
def getResults(self):
return self.news.result()
def clear(self):
self.news.clear()
def resetPageNumber(self):
self.pageNumber = 1
'''
Example of GoogleNews usage.
'''
from GoogleNews import GoogleNews
from pprint import pprint
news = GoogleNews()
news.setlang('en')
news.setencode('utf-8')
news.setperiod('3d')
news.search('Programming')
info = news.result()
print(news.total_count())
print(len(info))
news.get_page(2)
info = news.result()
print(len(info))
pprint(info)
#!/usr/bin/env python
# coding: utf-8
import pandas as pd
import jieba
from GoogleNews import GoogleNews
from bs4 import BeautifulSoup
import requests
googlenews = GoogleNews()
googlenews.setlang('cn')
googlenews.setperiod('d')
googlenews.setencode('utf-8')
googlenews.clear()
x = input("請輸入要搜尋的關鍵字，將為你搜集相關字詞內容:")
googlenews.search(x)
alldata = googlenews.result()
result = googlenews.gettext()
links = googlenews.get_links()
# print(type(result))
# print(len(result))
# print(alldata)
print()
for n in range(len(result)):
print(result[n])
print(links[n])
