def page_url(self, tv_listing):
"""
parses the imdb search url page and retrieves the first listing page url.
:param read: read object of a resource. This way we can stub it out, in such a way that we can send a url response
object or file read object
:return: returns url of the imdb listing page: http://www.imdb.com/title/tt0898266/?ref_=fn_tt_tt_1
"""
url = self.finder_url(tv_listing)
with contextlib.closing(urllib.urlopen(url)) as page_response:
helper = ScrapeHelper(page_response.read())
if helper.is_table_exists("findList"):
rows = helper.find_table_by_class("findList")
else:
url = self.finder_url(tv_listing, titles=True)
with contextlib.closing(
urllib.urlopen(url)) as page_response_1:
helper = ScrapeHelper(page_response_1.read())
rows = helper.find_table_by_class("findList")
top_result = rows[0].find('td').find('a').get('href')
return self.url + top_result
def get_scores(self, read):
"""
parses IMDB listing page and fetches relevant information
:param read: read object
:return: dict of popularity, best_rating, users, reviews, and external_reviews
"""
helper = ScrapeHelper(read)
popularity = self.getPopularity(helper)
popularity_change = self.meter_change(helper)
score_div = helper.find_div_by_itemtype(
'http://schema.org/AggregateRating')
rating = float(
helper.find_by_itemprop('span', 'ratingValue',
score_div).text.replace(",", ""))
best_rating = int(
helper.find_by_itemprop('span', 'bestRating',
score_div).text.replace(",", ""))
anchors = helper.find_all_anchors(score_div)
users, reviews, external_reviews = '', '', ''
for anchor in anchors:
href = anchor.get('href').split('?')[0]
count = long(self.getCount(anchor))
if href == 'ratings':
users = count
elif href == 'reviews':
reviews = count
elif href == 'externalreviews':
external_reviews = count
return {
'popularity': popularity,
'popularity_change': popularity_change,
'rating': rating,
'best_rating': best_rating,
'users': users,
'reviews': reviews,
'external_reviews': external_reviews
}
def get_scores(self, read):
"""
fetches raing, bestrating, worstrating, users info from the listing page url
:param read: read object
:return: dict
"""
helper = ScrapeHelper(read)
by_id = helper.find_by_id('div', 'all-critics-numbers')
all_critic = {
'rating':
self.getCount(helper.ratingValue_in_span(by_id)),
'bestrating':
self.getCount(helper.rating_in_meta('bestrating', by_id)),
'worstrating':
self.getCount(helper.rating_in_meta('worstrating', by_id)),
'users':
self.getCount(
helper.rating_in_meta('reviewCount ratingCount', by_id))
}
audience_score = helper.find_by_class('div', 'audience-score meter')
avg_audience = {
'rating':
self.getCount(helper.ratingValue_in_span(audience_score)),
'best_rating':
self.getCount(helper.rating_in_meta('bestrating', audience_score)),
'worst_rating':
self.getCount(helper.rating_in_meta('worstrating',
audience_score)),
'users':
self.getCount(helper.rating_in_meta('ratingCount', audience_score))
}
time.sleep(1)
return {'all_critic': all_critic, 'avg_audience': avg_audience}
def parse_search_page(self, read, type_):
helper = ScrapeHelper(read)
by_id = helper.find_by_id('ul', type_ + '_results_ul')
return self.url + helper.find_all_anchors(by_id)[0].get('href')
def get_scores(self, read):
"""
fetches raing, bestrating, worstrating, users info from the listing page url
:param read: read object
:return: dict
"""
helper = ScrapeHelper(read)
by_id = helper.find_by_id("div", "all-critics-numbers")
all_critic = {
"rating": self.getCount(helper.ratingValue_in_span(by_id)),
"bestrating": self.getCount(helper.rating_in_meta("bestrating", by_id)),
"worstrating": self.getCount(helper.rating_in_meta("worstrating", by_id)),
"users": self.getCount(helper.rating_in_meta("reviewCount ratingCount", by_id)),
}
audience_score = helper.find_by_class("div", "audience-score meter")
avg_audience = {
"rating": self.getCount(helper.ratingValue_in_span(audience_score)),
"best_rating": self.getCount(helper.rating_in_meta("bestrating", audience_score)),
"worst_rating": self.getCount(helper.rating_in_meta("worstrating", audience_score)),
"users": self.getCount(helper.rating_in_meta("ratingCount", audience_score)),
}
time.sleep(1)
return {"all_critic": all_critic, "avg_audience": avg_audience}
def parse_search_page(self, read, type_):
helper = ScrapeHelper(read)
by_id = helper.find_by_id("ul", type_ + "_results_ul")
return self.url + helper.find_all_anchors(by_id)[0].get("href")
def test_meter_change_descend(self):
helper = ScrapeHelper(
open(
'/home/sarath/start-internet-idea/tvguide/resources/imdb_listing_with_popularity_descend.html',
'r').read())
print(self.imdb.meter_change(helper))