def scrape_movie(self):
imdb_movie_id = self.imdb_movie_id
self.scrape_main_page()
# load in all review pages
n=0
self.reviews = []
self.imdb_review_ranking_counter=0
while n < self.nreviews:
imdb_review_url=url_join(self.main_page_url,'reviews?start=%s' % n)
if n % 50 ==0 and self.debug:
print ' * n=%d/%d' % (n, self.nreviews)
self.reviews += self.get_reviews_from_page(imdb_review_url)
n+=10 # imdb pages increment in steps of 10
if self.nreview_limit is not None and n == self.nreview_limit:
break
def scrape_movie(self):
imdb_movie_id = self.imdb_movie_id
self.scrape_main_page()
# load in all review pages
n = 0
self.reviews = []
self.imdb_review_ranking_counter = 0
while n < self.nreviews:
imdb_review_url = url_join(self.main_page_url,
'reviews?start=%s' % n)
if n % 50 == 0 and self.debug:
print ' * n=%d/%d' % (n, self.nreviews)
self.reviews += self.get_reviews_from_page(imdb_review_url)
n += 10 # imdb pages increment in steps of 10
if self.nreview_limit is not None and n == self.nreview_limit:
break
def get_main_page_url(imdb_movie_id):
return url_join('http://www.imdb.com/title/','tt%07d' % imdb_movie_id)
def get_main_page_url(imdb_movie_id):
return url_join('http://www.imdb.com/title/', 'tt%07d' % imdb_movie_id)
