我正在使用以下代码查找源代码中与以下网页对应的所有 rowspan="7"。
http://www.sebi.gov.in/sebiweb/investment/FIILatestSE.jsp?period=month
令人惊讶的是,即使有一些 42 rowspan="7" , find_all 结果并没有显示所有这些,而只显示了其中的 22 个。为什么?
这是我的代码:
from bs4 import BeautifulSoup
import csv
import time
import mechanize
import cookielib
# Browser
br = mechanize.Browser()
# Cookie Jar
cj = cookielib.LWPCookieJar()
br.set_cookiejar(cj)
# Browser options
br.set_handle_equiv(True)
br.set_handle_redirect(True)
br.set_handle_referer(True)
br.set_handle_robots(False)
# Follows refresh 0 but not hangs on refresh > 0
br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1)
# Want debugging messages?
#br.set_debug_http(True)
#br.set_debug_redirects(True)
#br.set_debug_responses(True)
br.addheaders = [('User-agent', 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0.1')]
print "Obtaining FII data from SEBI..."
r = br.open('http://www.sebi.gov.in/sebiweb/investment/FIILatestSE.jsp?period=month')
data = r.read()
messages=[]
messages.append("FII data obtained from SEBI")
soup=BeautifulSoup(data)
list=soup.find_all(rowspan="7")