def find_matched_words_from_yahoo_ads():
query = request.form['query']
#yahooスポンサードサーチは単語ごとに区切るより一文にしたほうが広告出やすい
head = 'http://search.yahoo.co.jp/search/ss?p='
tail = '&ei=UTF-8&fr=top_ga1_sa&type=websearch&x=drt'
url = head + query + tail
y_ad_page = WebPage(url)
y_ad_page.fetch_html()
y_ad_page.fetch_ads()
naradeha_results = []
bracket_words = []
for ad in y_ad_page.ads:
ad.fetch_link_title()
naradeha_results.extend(ad.pick_characteristic_words())
bracket_words.extend(ad.pick_bracket_words())
# naradeharesults => [{'なら': {'before': ['。', 'あの', '今石洋之']}}]
# bracket_words => ['アスコルビン酸', 'メルトダウン']
stop_words = ['公式', '楽天', '当日', 'お急ぎ便', 'ココ', 'ここ', 'これ', 'コレ', 'こちら', '公式', '購入', '人気', '詳細', '送料無料', '配送無料', '価格', '激安', '無料', 'アマゾン', 'ヤフオク', '０', '１', '２', '３']
for num in range(0, 10):
stop_words.append(str(num))
results = naradeha_words_to_results(naradeha_results, stop_words)
for bracket_word in bracket_words:
is_including_stop_word = False
for stop_word in stop_words:
if stop_word in bracket_word:
is_including_stop_word = True
break
if is_including_stop_word:
continue
results.append(bracket_word)
return render_template('words.tmpl', words=results)
def scrape_from_nanapi_and_build_heading_tree():
query = request.form['query']
head = 'http://nanapi.jp/search/q:'
query_url = head + query
nanapi_search_result_page = WebPage(query_url)
nanapi_search_result_page.fetch_html()
urls = nanapi_search_result_page.find_urls_from_nanapi_search_result()
results = []
for url in urls:
# result_pageはnanapiの1記事
result_page = WebPage(url)
result_page.fetch_html()
result_page.set_title()
# task_steps => [task_step, task_step, ...]
result_page.build_heading_tree()
result = {'title': result_page.title, 'nodes': result_page.top_nodes, 'url': result_page.url}
results.append(result)
return render_template('headings_and_li_texts.tmpl', results=results)
def scrape_from_nanapi():
query = request.form['query']
head = 'http://nanapi.jp/search/q:'
query_url = head + query
nanapi_search_result_page = WebPage(query_url)
nanapi_search_result_page.fetch_html()
urls = nanapi_search_result_page.find_urls_from_nanapi_search_result()
tasks = []
for url in urls:
# result_pageはnanapiの1記事
result_page = WebPage(url)
result_page.fetch_html()
# task_steps => [task_step, task_step, ...]
task = result_page.find_task_from_nanapi_with_headings()
# task_steps[0].h2 => 'はじめに'
# task_steps[0].h3s[0] => 'はじめに'
tasks.append(task)
# tasks => [task, task, ...]
# tasks[0][0].h2 => 'はじめに'
return render_template('nanapi_tasks.tmpl', tasks=tasks)
def yahoo_sponsored_results():
query = request.form['query']
#yahooスポンサードサーチは単語ごとに区切るより一文にしたほうが広告出やすい
head = 'http://search.yahoo.co.jp/search/ss?p='
tail = '&ei=UTF-8&fr=top_ga1_sa&type=websearch&x=drt'
url = head + query + tail
y_ad_page = WebPage(url)
y_ad_page.fetch_html()
y_ad_page.fetch_ads()
result_words = []
key_phrases_of_ads = []
Engine = SearchEngine()
for ad in y_ad_page.ads:
result_words.extend(ad.pick_nouns_and_verbs(ad.title))
result_words.extend(ad.pick_nouns_and_verbs(ad.snippet))
#key_phrases_of_ads.append(Engine.yahoo_key_phrase(ad.title))
#key_phrases_of_ads.append(Engine.yahoo_key_phrase(ad.snippet))
results = to_ranked_items(result_words)
#return ad_template.render(items=results)
return render_template('find_words_with_yahoo_ads.tmpl',
items=results)
from bing_api import Bing
import os
import constants
from web_page import WebPage
if __name__ == '__main__':
bing = Bing()
if not os.path.exists(constants.FETCHED_PAGES_DIR_NAME):
os.mkdir(constants.FETCHED_PAGES_DIR_NAME)
os.chdir(constants.FETCHED_PAGES_DIR_NAME)
results = bing.web_search(query=constants.QUERY,
num_of_results=constants.NUM_OF_FETCHED_PAGES,
keys=['Url'])
for i, result in enumerate(results):
page = WebPage(result['Url'])
page.fetch_html()
f = open('%s_%s.html' % (constants.QUERY, str(i)), 'w')
f.write(page.html_body)
f.close()
from bing_api import Bing
import os
import constants
from web_page import WebPage
if __name__ == '__main__':
bing = Bing()
if not os.path.exists(constants.FETCHED_PAGES_DIR_NAME):
os.mkdir(constants.FETCHED_PAGES_DIR_NAME)
os.chdir(constants.FETCHED_PAGES_DIR_NAME)
results = bing.web_search(query=constants.QUERY,
num_of_results=constants.NUM_OF_FETCHED_PAGES,
keys=['Url'])
for i, result in enumerate(results):
page = WebPage(result['Url'])
page.fetch_html()
f = open('%s_%s.html' % (constants.QUERY, str(i)), 'w')
f.write(page.html_body)
f.close()