简介
google 模块是谷歌搜索引擎python接口，系用urllib2在google上进行搜索，使用BeautifulSoup进行解释外部封装，非google官方接口。
功能：谷歌搜索引擎python接口
类型：外部模块
当前版本：1.0.5（查看日期2013-12-22）
月下载量：1万左右
平台：跨平台
安装
从https://pypi.python.org/pypi/setuptools下载最新版本的setuptools。google模块依赖setuptools2.0。setuptools是安装其他模块的基础，建议通过手动安装保持最新版本。
安装方法：
# tar xzvf setuptools-2.0.tar.gz
# cd setuptools-2.0
# python setup.py install
# easy_install pip
# pip install BeautifulSoup
# pip install google使用
>>> from google import search
>>> for url in search('python', tld='com.hk',, stop=2):
... print(url)
...
http://www.python.org/
http://www.python.org/getit/
http://www.python.org/doc/
http://www.python.org/getit/releases/3.3.2/
http://www.python.org/getit/releases/2.7.5/
http://zh.wikipedia.org/zh-hk/Python
http://zh.wikipedia.org/wiki/PyPy
http://zh.wikipedia.org/wiki/%E5%8D%B3%E6%99%82%E7%B7%A8%E8%AD%AF
http://zh.wikipedia.org/wiki/%E5%90%89%E5%A4%9A%C2%B7%E8%8C%83%E7%BD%97%E8%8B%8F%E5%A7%86
http://zh.wikipedia.org/wiki/CPython
http://en.wikipedia.org/wiki/Python_(programming_language)
http://python.org.tw/
http://en.wikipedia.org/wiki/Burmese_python
http://en.wikipedia.org/wiki/Python_regius
http://news.nationalgeographic.com/news/2005/10/1006_051006_pythoneatsgator.html
http://www.animalpeoplenews.org/anp/2013/10/26/alligators-pigs-pythons-the-reptilian-ploy-to-resuscitate-sport-hunting/
Mom Wakes to Python Wrapped Around Toddler
http://www.codecademy.com/tracks/python
http://openhome.cc/Gossip/Python/
http://pythonline.com/
http://learnpythonthehardway.org/book/
http://www.learnpython.org/search(query, tld=’com’,, num=10, start=0, stop=None, pause=2.0): 使用谷歌搜索字符串query。返回结果为生成器。参数如下：
query (str) – 查询字符串。非URL编码格式。
tld (str) – 顶级域名Top level domain。比如com, com.hk。
lang (str) – 语言。
num(int) – 每页的结果数。
start(int) – 记录开始点。
stop(int) – 记录结束点。
pause(int) – HTTP请求之间的sleep秒数。
get_page(url)：使用cookiejar返回页面。相关变量如下：
url_home = “http://www.google.%(tld)s/“
url_search = “http://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&btnG=Google+Search“
url_next_page = “http://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&start=%(start)d“
url_search_num = “http://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&num=%(num)d&btnG=Google+Search“
url_next_page_num = “http://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&num=%(num)d&start=%(start)d“
源码
Google是一个相当小巧强悍的模块，代码只有200多行，是大家学习urlib2，BeautifulSoup的绝好资源，对如何发布python包也相当有借鉴意义。今后在urlib2等模块会深入Google模块，下面附上源码：
#!/usr/bin/env python# Python bindings to the Google search engine# Copyright (c) 2009-2013, Mario Vilas# All rights reserved.## Redistribution and use in source and binary forms, with or without# modification, are permitted provided that the following conditions are met:## * Redistributions of source code must retain the above copyright notice,# this list of conditions and the following disclaimer.# * Redistributions in binary form must reproduce the above copyright# notice,this list of conditions and the following disclaimer in the# documentation and/or other materials provided with the distribution.# * Neither the name of the copyright holder nor the names of its# contributors may be used to endorse or promote products derived from# this software without specific prior written permission.## THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE# POSSIBILITY OF SUCH DAMAGE.__all__ = ['search']import osimport sysimport timeif sys.version_info[0] > 2:
from http.cookiejar import LWPCookieJar from urllib.request import Request, urlopen from urllib.parse import quote_plus, urlparse, parse_qselse:
from cookielib import LWPCookieJar from urllib import quote_plus from urllib2 import Request, urlopen from urlparse import urlparse, parse_qs# Lazy import of BeautifulSoup.BeautifulSoup = None# URL templates to make Google searches.url_home = "http://www.google.%(tld)s/"url_search = "http://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&btnG=Google+Search"url_next_page = "http://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&start=%(start)d"url_search_num = "http://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&num=%(num)d&btnG=Google+Search"url_next_page_num = "http://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&num=%(num)d&start=%(start)d"# Cookie jar. Stored at the user's home folder.home_folder = os.getenv('HOME')if not home_folder:
home_folder = os.getenv('USERHOME')
if not home_folder:
home_folder = '.' # Use the current folder on error.cookie_jar = LWPCookieJar(os.path.join(home_folder, '.google-cookie'))try:
cookie_jar.load()except Exception:
pass# Request the given URL and return the response page, using the cookie jar.def get_page(url):
"""
Request the given URL and return the response page, using the cookie jar.
@type url: str
@param url: URL to retrieve.
@rtype: str
@return: Web page retrieved for the given URL.
@raise IOError: An exception is raised on error.
@raise urllib2.URLError: An exception is raised on error.
@raise urllib2.HTTPError: An exception is raised on error.
"""
request = Request(url)
request.add_header('User-Agent',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0)')
cookie_jar.add_cookie_header(request)
response = urlopen(request)
cookie_jar.extract_cookies(response, request)
html = response.read()
response.close()
cookie_jar.save()
return html# Filter links found in the Google result pages HTML code.# Returns None if the link doesn't yield a valid result.def filter_result(link):
try:
# Valid results are absolute URLs not pointing to a Google domain
# like images.google.com or googleusercontent.com
o = urlparse(link, 'http')
if o.netloc and 'google' not in o.netloc:
return link # Decode hidden URLs.
if link.startswith('/url?'):
link = parse_qs(o.query)['q'][0]
# Valid results are absolute URLs not pointing to a Google domain
# like images.google.com or googleusercontent.com
o = urlparse(link, 'http')
if o.netloc and 'google' not in o.netloc:
return link # Otherwise, or on error, return None.
except Exception:
pass
return None# Returns a generator that yields URLs.def search(query, tld='com', lang='en', num=10, start=0, stop=None, pause=2.0):
"""
Search the given query string using Google.
@type query: str
@param query: Query string. Must NOT be url-encoded.
@type tld: str
@param tld: Top level domain.
@type lang: str
@param lang: Languaje.
@type num: int
@param num: Number of results per page.
@type start: int
@param start: First result to retrieve.
@type stop: int
@param stop: Last result to retrieve.
Use C{None} to keep searching forever.
@type pause: float
@param pause: Lapse to wait between HTTP requests.
A lapse too long will make the search slow, but a lapse too short may
cause Google to block your IP. Your mileage may vary!
@rtype: generator
@return: Generator (iterator) that yields found URLs. If the C{stop}
parameter is C{None} the iterator will loop forever.
"""
# Lazy import of BeautifulSoup.
# Try to use BeautifulSoup 4 if available, fall back to 3 otherwise.
global BeautifulSoup if BeautifulSoup is None:
try:
from bs4 import BeautifulSoup except ImportError:
from BeautifulSoup import BeautifulSoup # Set of hashes for the results found.
# This is used to avoid repeated results.
hashes = set()
# Prepare the search string.
query = quote_plus(query)
# Grab the cookie from the home page.
get_page(url_home % vars())
# Prepare the URL of the first request.
if start:
if num == 10:
url = url_next_page % vars()
else:
url = url_next_page_num % vars()
else:
if num == 10:
url = url_search % vars()
else:
url = url_search_num % vars()
# Loop until we reach the maximum result, if any (otherwise, loop forever).
while not stop or start < stop:
# Sleep between requests.
time.sleep(pause)
# Request the Google Search results page.
html = get_page(url)
# Parse the response and process every anchored URL.
soup = BeautifulSoup(html)
anchors = soup.find(id='search').findAll('a')
for a in anchors:
# Get the URL from the anchor tag.
try:
link = a['href']
except KeyError:
continue
# Filter invalid links and links pointing to Google itself.
link = filter_result(link)
if not link:
continue
# Discard repeated results.
h = hash(link)
if h in hashes:
continue
hashes.add(h)
# Yield the result.
yield link # End if there are no more results.
if not soup.find(id='nav'):
break
# Prepare the URL for the next request.
start += num if num == 10:
url = url_next_page % vars()
else:
url = url_next_page_num % vars()# When run as a script...if __name__ == "__main__":
from optparse import OptionParser, IndentedHelpFormatter class BannerHelpFormatter(IndentedHelpFormatter):
"Just a small tweak to optparse to be able to print a banner."
def __init__(self, banner, *argv, **argd):
self.banner = banner
IndentedHelpFormatter.__init__(self, *argv, **argd)
def format_usage(self, usage):
msg = IndentedHelpFormatter.format_usage(self, usage)
return '%s\n%s' % (self.banner, msg)
# Parse the command line arguments.
formatter = BannerHelpFormatter(
"Python script to use the Google search engine\n"
"By Mario Vilas (mvilas at gmail dot com)\n"
"https://github.com/MarioVilas/google\n"
)
parser = OptionParser(formatter=formatter)
parser.set_usage("%prog [options] query")
parser.add_option("--tld", metavar="TLD", type="string", default="com",
help="top level domain to use [default: com]")
parser.add_option("--lang", metavar="LANGUAGE", type="string", default="en",
help="produce results in the given language [default: en]")
parser.add_option("--num", metavar="NUMBER", type="int", default=10,
help="number of results per page [default: 10]")
parser.add_option("--start", metavar="NUMBER", type="int", default=0,
help="first result to retrieve [default: 0]")
parser.add_option("--stop", metavar="NUMBER", type="int", default=0,
help="last result to retrieve [default: unlimited]")
parser.add_option("--pause", metavar="SECONDS", type="float", default=2.0,
help="pause between HTTP requests [default: 2.0]")
(options, args) = parser.parse_args()
query = ' '.join(args)
if not query:
parser.print_help()
sys.exit(2)
params = [(k,v) for (k,v) in options.__dict__.items() if not k.startswith('_')]
params = dict(params)
# Run the query.
for url in search(query, **params):
print(url)参考资料
类型：翻译加整理
