def espn_schedule():
for year in [2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014]:
time.sleep(30)
for month in [3, 4, 5, 6, 7, 8, 9, 10]:
for day in [1, 8, 15, 22, 29]:
if month == 3:
if day != 29:
continue
time.sleep(2)
if day < 10:
day = '0%s' % (day)
if month < 10:
month = '0%s' % (month)
date = int('%s%s%s' % (year, month, day))
browser = create_browser()
page = browser.open('http://espn.go.com/mlb/schedule?date=%s' % date)
html = parse_html(page.read())
for tr in html.cssselect('.mod-content tr'):
for a in tr.cssselect('td a'):
link = a.get('href')
print link
try:
espn_id = int(link.split('?id=')[1])
print espn_id
get_or_create_espnid(espn_id=espn_id, date=date)
except:
continue
break
def main():
global news_scraper
opener = urllib2.build_opener()
opener.addheaders = [
('User-agent', 'Mozilla/5.0'),
('Referer', news_scraper.base_url)
]
urllib2.install_opener(opener)
error_count = 0
while error_count < 3:
try:
html = scraperwiki.scrape(news_scraper.base_url)
except urllib2.URLError, e:
print 'Cannot reach the server:',
if hasattr(e, 'reason'): print e.reason
elif hasattr(e, 'code'): print e.code
error_count += 1
try:
html = html.decode(news_scraper.page_encoding)
except UnicodeDecodeError:
encoded = ''
for word in html.split(' '):
try:
encoded += word.decode(news_scraper.page_encoding) + ' '
except UnicodeDecodeError:
pass
html = encoded.rstrip()
num_of_article = scrape(parse_html(html))
print 'Headline ,', num_of_article, 'article(s)'
break
def main():
global base_url, page_num_of_article, page_start, page_step, page_encoding, page_sleep, count
count = 0
last_page = scraperwiki.sqlite.get_var('last_page', -1)
latest_article = None
start_over = False
if last_page == -1:
last_page = page_start
latest_article = scraperwiki.sqlite.get_var('latest_article', None)
start_over = True
opener = urllib2.build_opener()
opener.addheaders = [
('User-agent', 'Mozilla/5.0'),
('Referer', base_url)
]
urllib2.install_opener(opener)
error_count = 0
num_of_article = page_num_of_article
while num_of_article == page_num_of_article:
page_url = build_url(last_page)
try:
html = scraperwiki.scrape(page_url)
except urllib2.URLError, e:
print 'Cannot reach the server:',
if hasattr(e, 'reason'): print e.reason
elif hasattr(e, 'code'): print e.code
error_count += 1
if error_count < 3: continue
else: break
try:
html = html.decode(page_encoding)
except UnicodeDecodeError:
encoded = ''
for word in html.split(' '):
try:
encoded += word.decode(page_encoding) + ' '
except UnicodeDecodeError:
pass
html = encoded.rstrip()
num_of_article = scrape(parse_html(html), latest_article, start_over)
page = last_page / page_step
if (page_start == 0): page += 1
scraperwiki.sqlite.save_var('last_page', last_page)
print 'Page', page, ',', num_of_article, 'article(s)'
last_page += page_step
if not page_exists(html, last_page): break
time.sleep(page_sleep)
def main():
global base_url, page_num_of_article, page_start, page_step, page_encoding, page_sleep, count
count = 0
last_page = scraperwiki.sqlite.get_var('last_page', -1)
latest_article = None
start_over = False
if last_page == -1:
last_page = page_start
latest_article = scraperwiki.sqlite.get_var('latest_article', None)
start_over = True
opener = urllib2.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0'), ('Referer', base_url)]
urllib2.install_opener(opener)
error_count = 0
num_of_article = page_num_of_article
while num_of_article == page_num_of_article:
page_url = build_url(last_page)
try:
html = scraperwiki.scrape(page_url)
except urllib2.URLError, e:
print 'Cannot reach the server:',
if hasattr(e, 'reason'): print e.reason
elif hasattr(e, 'code'): print e.code
error_count += 1
if error_count < 3: continue
else: break
try:
html = html.decode(page_encoding)
except UnicodeDecodeError:
encoded = ''
for word in html.split(' '):
try:
encoded += word.decode(page_encoding) + ' '
except UnicodeDecodeError:
pass
html = encoded.rstrip()
num_of_article = scrape(parse_html(html), latest_article, start_over)
page = last_page / page_step
if (page_start == 0): page += 1
scraperwiki.sqlite.save_var('last_page', last_page)
print 'Page', page, ',', num_of_article, 'article(s)'
last_page += page_step
if not page_exists(html, last_page): break
time.sleep(page_sleep)
