Python爬虫包 BeautifulSoup 学习（三） 实例

一步一步构建一个爬虫实例，抓取糗事百科的段子

先不用beautifulsoup包来进行解析

第一步，访问网址并抓取源码

# -*- coding: utf-8 -*-
# @Author: HaonanWu
# @Date:   2016-12-22 16:16:08
# @Last Modified by:   HaonanWu
# @Last Modified time: 2016-12-22 20:17:13

import urllib
import urllib2
import re
import os

if __name__ == '__main__':
# 访问网址并抓取源码
url = 'http://www.qiushibaike.com/textnew/page/1/?s=4941357'
user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'
headers = {'User-Agent':user_agent}
try:
request = urllib2.Request(url = url, headers = headers)
response = urllib2.urlopen(request)
content = response.read()
except urllib2.HTTPError as e:
print e
exit()
except urllib2.URLError as e:
print e
exit()
print content.decode('utf-8')

第二步，利用正则表达式提取信息

首先先观察源码中，你需要的内容的位置以及如何识别

然后用正则表达式去识别读取

注意正则表达式中的 . 是不能匹配\n的，所以需要设置一下匹配模式。

# -*- coding: utf-8 -*-
# @Author: HaonanWu
# @Date:   2016-12-22 16:16:08
# @Last Modified by:   HaonanWu
# @Last Modified time: 2016-12-22 20:17:13

import urllib
import urllib2
import re
import os

if __name__ == '__main__':
# 访问网址并抓取源码
url = 'http://www.qiushibaike.com/textnew/page/1/?s=4941357'
user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'
headers = {'User-Agent':user_agent}
try:
request = urllib2.Request(url = url, headers = headers)
response = urllib2.urlopen(request)
content = response.read()
except urllib2.HTTPError as e:
print e
exit()
except urllib2.URLError as e:
print e
exit()

regex = re.compile('<div class="content">.*?<span>(.*?)</span>.*?</div>', re.S)
items = re.findall(regex, content)

# 提取数据
# 注意换行符，设置 . 能够匹配换行符
for item in items:
print item

第三步，修正数据并保存到文件中

# -*- coding: utf-8 -*-
# @Author: HaonanWu
# @Date:   2016-12-22 16:16:08
# @Last Modified by:   HaonanWu
# @Last Modified time: 2016-12-22 21:41:32

import urllib
import urllib2
import re
import os

if __name__ == '__main__':
# 访问网址并抓取源码
url = 'http://www.qiushibaike.com/textnew/page/1/?s=4941357'
user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'
headers = {'User-Agent':user_agent}
try:
request = urllib2.Request(url = url, headers = headers)
response = urllib2.urlopen(request)
content = response.read()
except urllib2.HTTPError as e:
print e
exit()
except urllib2.URLError as e:
print e
exit()

regex = re.compile('<div class="content">.*?<span>(.*?)</span>.*?</div>', re.S)
items = re.findall(regex, content)

# 提取数据
# 注意换行符，设置 . 能够匹配换行符
path = './qiubai'
if not os.path.exists(path):
os.makedirs(path)
count = 1
for item in items:
#整理数据，去掉\n,将<br/>换成\n
item = item.replace('\n', '').replace('<br/>', '\n')
filepath = path + '/' + str(count) + '.txt'
f = open(filepath, 'w')
f.write(item)
f.close()
count += 1

第四步，将多个页面下的内容都抓取下来

# -*- coding: utf-8 -*-
# @Author: HaonanWu
# @Date:   2016-12-22 16:16:08
# @Last Modified by:   HaonanWu
# @Last Modified time: 2016-12-22 20:17:13

import urllib
import urllib2
import re
import os

if __name__ == '__main__':
# 访问网址并抓取源码
path = './qiubai'
if not os.path.exists(path):
os.makedirs(path)
user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'
headers = {'User-Agent':user_agent}
regex = re.compile('<div class="content">.*?<span>(.*?)</span>.*?</div>', re.S)
count = 1
for cnt in range(1, 35):
print '第' + str(cnt) + '轮'
url = 'http://www.qiushibaike.com/textnew/page/' + str(cnt) + '/?s=4941357'
try:
request = urllib2.Request(url = url, headers = headers)
response = urllib2.urlopen(request)
content = response.read()
except urllib2.HTTPError as e:
print e
exit()
except urllib2.URLError as e:
print e
exit()
# print content

# 提取数据
# 注意换行符，设置 . 能够匹配换行符
items = re.findall(regex, content)

# 保存信息
for item in items:
#   print item
#整理数据，去掉\n,将<br/>换成\n
item = item.replace('\n', '').replace('<br/>', '\n')
filepath = path + '/' + str(count) + '.txt'
f = open(filepath, 'w')
f.write(item)
f.close()
count += 1

print '完成'

使用BeautifulSoup对源码进行解析

# -*- coding: utf-8 -*-
# @Author: HaonanWu
# @Date:   2016-12-22 16:16:08
# @Last Modified by:   HaonanWu
# @Last Modified time: 2016-12-22 21:34:02

import urllib
import urllib2
import re
import os
from bs4 import BeautifulSoup

if __name__ == '__main__':
url = 'http://www.qiushibaike.com/textnew/page/1/?s=4941357'
user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'
headers = {'User-Agent':user_agent}
request = urllib2.Request(url = url, headers = headers)
response = urllib2.urlopen(request)
# print response.read()
soup_packetpage = BeautifulSoup(response, 'lxml')
items = soup_packetpage.find_all("div", class_="content")

for item in items:
try:
content = item.span.string
except AttributeError as e:
print e
exit()

if content:
print content + "\n"

这是用BeautifulSoup去抓取书本以及其价格的代码

可以通过对比得出到bs4对标签的读取以及标签内容的读取

（因为我自己也没有学到这一部分，目前只能依葫芦画瓢地写）

# -*- coding: utf-8 -*-
# @Author: HaonanWu
# @Date:   2016-12-22 20:37:38
# @Last Modified by:   HaonanWu
# @Last Modified time: 2016-12-22 21:27:30
import urllib2
import urllib
import re

from bs4 import BeautifulSoup

url = "https://www.packtpub.com/all"
try:
html = urllib2.urlopen(url)
except urllib2.HTTPError as e:
print e
exit()

soup_packtpage = BeautifulSoup(html, 'lxml')
all_book_title = soup_packtpage.find_all("div", class_="book-block-title")

price_regexp = re.compile(u"\s+\$\s\d+\.\d+")

for book_title in all_book_title:
try:
print "Book's name is " + book_title.string.strip()
except AttributeError as e:
print e
exit()
book_price = book_title.find_next(text=price_regexp)
try:
print "Book's price is "+ book_price.strip()
except AttributeError as e:
print e
exit()
print ""