def scrape(html, filter=r".*"):
soup = BeautifulSoup(html)
tbl = soup.find_all('tr')
for tr in tbl[1:]:
rec = TalkRecord()
rec.series = "cornell-scan"
rec.datetime = scrape_date(tr)
if not re.match(filter, rec.date()):
continue
rec.speaker = scrape_speaker(tr)
rec.title = scrape_title(tr)
rec.url = scrape_url(tr)
rec.blurb = scrape_blurb(rec.url)
rec.write()
def scrape(html, filter=r".*"):
soup = BeautifulSoup(html)
dates = soup.find_all('h4')
patt1 = re.compile("\s*[^:]*:(.*\(.*\))\s*-\s*([^\n]*)")
for date in dates:
rec = TalkRecord()
rec.series = "cornell-cam"
rec.datetime = scrape_date(date)
if not re.match(filter, rec.date()):
continue
infos = date.find_next_sibling('h5')
if not infos:
continue
m = patt1.match(infos.get_text().encode("utf8"))
if not m:
continue
rec.speaker = m.group(1)
rec.title = m.group(2)
rec.url = infos.find('a').get('href')
rec.blurb = scrape_blurb(rec.url)
rec.write()
