def search():
search_phrase = utils.get_keywords(3)
needl.log.info('Searching Google for: %s', search_phrase)
browser = utils.get_browser()
browser.get(GOOGLE)
search_form = browser.find_element_by_id('tsf')
browser.find_elements_by_css_selector('input[name=q]')[0].send_keys(
search_phrase)
search_form.submit()
results_count = browser.find_element_by_id('resultStats').text.rstrip()
needl.log.debug('%s for %s', results_count, search_phrase)
if needl.settings['google']['click_through']:
links = [
link for link in browser.find_elements_by_css_selector('h3.r > a')
if utils.url_is_absolute(link.get_attribute('href'))
]
if len(links) > 0:
link = needl.rand.choice(links).get_attribute('href')
needl.log.info('Visiting %s', link)
browser.get(link)
click_depth = needl.settings['google']['click_depth']
if click_depth > 0:
utils.process_click_depth(browser, click_depth)
browser.quit()
def search():
search_phrase = utils.get_keywords(3)
needl.log.info('Searching Google for: %s', search_phrase)
browser = utils.get_browser()
page = browser.get(GOOGLE)
search_form = page.soup.select('form[name=f]')[0]
search_form.select('input[name=q]')[0]['value'] = search_phrase
try:
search_form.select('input[name=btnI]')[0][
'name'] = '' # hack so mechanicalsoup doesn't request I'm Feeling Lucky results
except IndexError:
pass
search_results = browser.submit(search_form, page.url)
results_count = search_results.soup.find('div',
id='resultStats').text.rstrip()
needl.log.debug('%s for %s', results_count, search_phrase)
if needl.settings['google']['click_through']:
links = [
link for link in search_results.soup.select('h3.r > a')
if utils.url_is_absolute(link.get('href'))
]
if len(links) > 0:
link = needl.rand.choice(links).get('href')
needl.log.info('Visiting %s', link)
page = browser.get(link)
click_depth = needl.settings['google']['click_depth']
if click_depth > 0:
utils.process_click_depth(browser, page, click_depth)
def visit():
site = get_random_site()
needl.log.info('Visiting %s', site)
browser = utils.get_browser()
browser.get(site)
utils.process_click_depth(browser, needl.settings['alexa']['click_depth'])
def get_user():
first = utils.get_line(needl.args.datadir + '/first-names.txt').title()
last = utils.get_line(needl.args.datadir + '/last-names.txt').title()
needl.log.info('Finding Twitter user: "******"', first, last)
browser = utils.get_browser()
page = browser.get(TWITTER.format(first + last))
if page.status_code is not 200:
needl.log.debug('Twitter user "%s %s" not found', first, last)
return
def get_user():
first = utils.get_line(needl.args.datadir + '/first-names.txt').title()
last = utils.get_line(needl.args.datadir + '/last-names.txt').title()
needl.log.info('Finding Twitter user: "******"', first, last)
browser = utils.get_browser()
browser.get(TWITTER.format(first + last))
if "Sorry, that page doesn’t exist!" in browser.page_source:
needl.log.debug('Twitter user "%s %s" not found', first, last)
browser.quit()
def search():
hashtag = '#' + utils.get_keywords(1)
needl.log.info('Searching Twitter for: "%s"', hashtag)
browser = utils.get_browser()
browser.get(TWITTER.format('search?f=tweets&vertical=default&q=' + url.quote_plus(hashtag) + '&src=typd'))
try:
first_tweet_by = browser.find_elements_by_css_selector('.stream-item > .tweet')[0].get_attribute('data-screen-name')
needl.log.info('Latest Tweet for %s by %s', hashtag, first_tweet_by)
except:
pass
finally:
browser.quit()
def search():
hashtag = '#' + utils.get_keywords(1)
needl.log.info('Searching Twitter for: "%s"', hashtag)
browser = utils.get_browser()
page = browser.get(
TWITTER.format('search?f=tweets&vertical=default&q=' +
url.quote_plus(hashtag) + '&src=typd'))
try:
first_tweet_by = page.soup.select(
'.stream-item > .tweet')[0]['data-screen-name']
needl.log.info('Latest Tweet for %s by %s', hashtag, first_tweet_by)
except:
pass
