Python的beautifulsoup不敛全表

Question

我不知道如果不抓住全表，因为mechanize

这工作：

from bs4 import BeautifulSoup 
import requests 

page = 'http://www.airchina.com.cn/www/jsp/airlines_operating_data/exlshow_en.jsp' 
r = requests.get(page) 

r.encoding = 'utf-8' 
soup = BeautifulSoup(r.text) 

div = soup.find('div', class_='mainRight').find_all('div')[1] 
table = div.find('table', recursive=False) 

for row in table.find_all('tr', recursive=False): 
    for cell in row('td', recursive=False): 
     print cell.text.split() 

但这并不：

import mechanize 
from bs4 import BeautifulSoup 
import requests 

URL='http://www.airchina.com.cn/www/jsp/airlines_operating_data/exlshow_en.jsp' 
control_year=['2006', '2007', '2008', '2009', '2010', '2011', '2012', '2013', '2014'] 
control_month=['01', '02', '03', '04', '05', '06', '07', '08', '09', '10', '11', '12'] 

br = mechanize.Browser() 
r=br.open(URL) 

br.select_form("exl") 
control_m = br.form.find_control('month') 
control_y = br.form.find_control('year') 

br[control_m.name]=['06'] 
br[control_y.name]=['2012'] 
response = br.submit() 
soup = BeautifulSoup(response,'html.parser') 
#div = soup.find('div', class_='mainRight') 


div = soup.find('div', class_='mainRight').find_all('div')[1] 
table = div.find('table', recursive=False) 
for row in table.find_all('tr', recursive=False): 
    for cell in row('td', recursive=False): 
     print cell.text.strip() 

使用mechanize只生产以下，即使在萤火虫我看到所有的tr和td

Jun 2012 
% change vs Jun 2011 
% change vs May 2012 
Cumulative Jun 2012 
% cumulative change 

Answer 1

将两者结合使用时没有问题，因此它可能与您正在使用的html.parser有关。

import mechanize 
from bs4 import BeautifulSoup 

URL = ('http://www.airchina.com.cn/www/jsp/airlines_operating_data/' 
     'exlshow_en.jsp') 
control_year = ['2006', '2007', '2008', '2009', '2010', '2011', '2012', '2013', 
       '2014'] 
control_month = ['01', '02', '03', '04', '05', '06', '07', '08', '09', '10', 
       '11', '12'] 

br = mechanize.Browser() 
r = br.open(URL) 

br.select_form("exl") 
control_m = br.form.find_control('month') 
control_y = br.form.find_control('year') 

br[control_m.name] = ['06'] 
br[control_y.name] = ['2012'] 
response = br.submit() 

soup = BeautifulSoup(response) 

div = soup.find('div', class_='mainRight').find_all('div')[1] 
table = div.find('table', recursive=False) 

for row in table.find_all('tr', recursive=False): 
    for cell in row('td', recursive=False): 
     print cell.text.split()