Created
April 30, 2015 11:16
-
-
Save wjx/6091f3656297c693f9dd to your computer and use it in GitHub Desktop.
Archive hi.baidu.com articles.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import os | |
import sys | |
import io | |
import re | |
import requests | |
from bs4 import BeautifulSoup | |
from time import sleep | |
import random | |
username = raw_input('Enter user name:') | |
archive_base = 'http://hi.baidu.com/' + username + '/archive' | |
#get year list | |
r = requests.get(archive_base) | |
if r.status_code is not 200: | |
print "Request archive base failed." | |
sys.exit() | |
s = BeautifulSoup(r.text) | |
fiList = s.find('div', id='fiList') | |
year_as = fiList.find_all('a', recursive=False) | |
year_hrefs = [a.get('href') for a in year_as] | |
for year_href in year_hrefs: | |
item_year = year_href[year_href.rfind('=') + 1:] | |
r = requests.get(year_href) | |
if r.url == 'http://hi.baidu.com/com/error': | |
print "requests for {0} failed!".format(year_page) | |
break | |
r.encoding = 'utf8' | |
year_soup = BeautifulSoup(r.text) | |
items = year_soup.find_all('a', class_='blog-item blog-text') | |
print "Year {0} ,{1} articles.".format(item_year, len(items)) | |
for item in items: | |
item_month = item.find_previous('h3', class_='month-tip').string | |
item_time = item.find_next('span', class_='info-time').string | |
item_href = item.get('href') | |
#for debugging | |
#print('item_month=' + item_month) | |
#print('item_time=' + item_time) | |
#print('item_href=' + item_href) | |
#print('item_year=' + item_year) | |
item_r = requests.get(item_href) | |
if item_r.status_code is not 200: | |
print("requests for {0} failed!".format(item_href)) | |
item_r.encoding = 'utf8' | |
item_s = BeautifulSoup(item_r.text) | |
title = item_s.find(class_='title content-title').string | |
title = title.strip().replace(' ', '_') + item_time; | |
archive_dir = './archives' + os.sep + item_year + os.sep + item_month | |
try: | |
os.makedirs(archive_dir) | |
except OSError as exc: # Python >2.5 | |
if exc.errno == errno.EEXIST and os.path.isdir(path): | |
pass | |
else: | |
raise | |
dst_filename = archive_dir + os.sep + title + '.html' | |
f = io.open(dst_filename, 'w', encoding='utf8') | |
f.write(item_r.text) | |
f.close() | |
sleep(random.randint(3, 10)); | |
#for debugging | |
#print('exiting.') | |
#sys.exit() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment