Python爬虫常用库的使用

builtwith的使用

Requests库的使用

实例引入

import requests

response = requests.get('https://www.baidu.com/')
print(type(response))
print(response.status_code)
print(type(response.text))
print(response.text)
print(response.cookies)

各种请求方式

import requests
requests.post('http://httpbin.org/post')
requests.put('http://httpbin.org/put')
requests.delete('http://httpbin.org/delete')
requests.head('http://httpbin.org/get')
requests.options('http://httpbin.org/get')

基本GET请求

基本写法

import requests

response = requests.get('http://httpbin.org/get')
print(response.text)

带参数GET请求

import requests
response = requests.get("http://httpbin.org/get?name=germey&age=22")
print(response.text)

import requests

data = {
    'name': 'germey',
    'age': 22
}
response = requests.get("http://httpbin.org/get", params=data)
print(response.text)

解析json

import requests
import json

response = requests.get("http://httpbin.org/get")
print(type(response.text))
print(response.json())
print(json.loads(response.text))
print(type(response.json()))

获取二进制数据

import requests

response = requests.get("https://github.com/favicon.ico")
print(type(response.text), type(response.content))
print(response.text)
print(response.content)

import requests

response = requests.get("https://github.com/favicon.ico")
with open('favicon.ico', 'wb') as f:
    f.write(response.content)
    f.close()

添加headers

import requests

response = requests.get("https://www.zhihu.com/explore")
print(response.text)

import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
}
response = requests.get("https://www.zhihu.com/explore", headers=headers)
print(response.text)

基本POST请求

import requests

data = {'name': 'germey', 'age': '22'}
response = requests.post("http://httpbin.org/post", data=data)
print(response.text)

import requests

data = {'name': 'germey', 'age': '22'}
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
}
response = requests.post("http://httpbin.org/post", data=data, headers=headers)
print(response.json())

reponse属性

import requests

response = requests.get('http://www.jianshu.com')
print(type(response.status_code), response.status_code)
print(type(response.headers), response.headers)
print(type(response.cookies), response.cookies)
print(type(response.url), response.url)
print(type(response.history), response.history)

状态码判断

import requests

response = requests.get('http://www.jianshu.com/hello.html')
exit() if not response.status_code == requests.codes.not_found else print('404 Not Found')

import requests

response = requests.get('http://www.jianshu.com')
exit() if not response.status_code == 200 else print('Request Successfully')

100: ('continue',),
101: ('switching_protocols',),
102: ('processing',),
103: ('checkpoint',),
122: ('uri_too_long', 'request_uri_too_long'),
200: ('ok', 'okay', 'all_ok', 'all_okay', 'all_good', '\\o/', '✓'),
201: ('created',),
202: ('accepted',),
203: ('non_authoritative_info', 'non_authoritative_information'),
204: ('no_content',),
205: ('reset_content', 'reset'),
206: ('partial_content', 'partial'),
207: ('multi_status', 'multiple_status', 'multi_stati', 'multiple_stati'),
208: ('already_reported',),
226: ('im_used',),

# Redirection.
300: ('multiple_choices',),
301: ('moved_permanently', 'moved', '\\o-'),
302: ('found',),
303: ('see_other', 'other'),
304: ('not_modified',),
305: ('use_proxy',),
306: ('switch_proxy',),
307: ('temporary_redirect', 'temporary_moved', 'temporary'),
308: ('permanent_redirect',
      'resume_incomplete', 'resume',), # These 2 to be removed in 3.0

# Client Error.
400: ('bad_request', 'bad'),
401: ('unauthorized',),
402: ('payment_required', 'payment'),
403: ('forbidden',),
404: ('not_found', '-o-'),
405: ('method_not_allowed', 'not_allowed'),
406: ('not_acceptable',),
407: ('proxy_authentication_required', 'proxy_auth', 'proxy_authentication'),
408: ('request_timeout', 'timeout'),
409: ('conflict',),
410: ('gone',),
411: ('length_required',),
412: ('precondition_failed', 'precondition'),
413: ('request_entity_too_large',),
414: ('request_uri_too_large',),
415: ('unsupported_media_type', 'unsupported_media', 'media_type'),
416: ('requested_range_not_satisfiable', 'requested_range', 'range_not_satisfiable'),
417: ('expectation_failed',),
418: ('im_a_teapot', 'teapot', 'i_am_a_teapot'),
421: ('misdirected_request',),
422: ('unprocessable_entity', 'unprocessable'),
423: ('locked',),
424: ('failed_dependency', 'dependency'),
425: ('unordered_collection', 'unordered'),
426: ('upgrade_required', 'upgrade'),
428: ('precondition_required', 'precondition'),
429: ('too_many_requests', 'too_many'),
431: ('header_fields_too_large', 'fields_too_large'),
444: ('no_response', 'none'),
449: ('retry_with', 'retry'),
450: ('blocked_by_windows_parental_controls', 'parental_controls'),
451: ('unavailable_for_legal_reasons', 'legal_reasons'),
499: ('client_closed_request',),

# Server Error.
500: ('internal_server_error', 'server_error', '/o\\', '✗'),
501: ('not_implemented',),
502: ('bad_gateway',),
503: ('service_unavailable', 'unavailable'),
504: ('gateway_timeout',),
505: ('http_version_not_supported', 'http_version'),
506: ('variant_also_negotiates',),
507: ('insufficient_storage',),
509: ('bandwidth_limit_exceeded', 'bandwidth'),
510: ('not_extended',),
511: ('network_authentication_required', 'network_auth', 'network_authentication'),

文件上传

import requests

files = {'file': open('favicon.ico', 'rb')}
response = requests.post("http://httpbin.org/post", files=files)
print(response.text)

获取cookie

import requests

response = requests.get("https://www.baidu.com")
print(response.cookies)
for key, value in response.cookies.items():
    print(key + '=' + value)

会话维持

模拟登录

import requests

requests.get('http://httpbin.org/cookies/set/number/123456789')
response = requests.get('http://httpbin.org/cookies')
print(response.text)

import requests

s = requests.Session()
s.get('http://httpbin.org/cookies/set/number/123456789')
response = s.get('http://httpbin.org/cookies')
print(response.text)

证书验证

import requests

response = requests.get('https://www.12306.cn')
print(response.status_code)

import requests
from requests.packages import urllib3
urllib3.disable_warnings()
response = requests.get('https://www.12306.cn', verify=False)
print(response.status_code)

import requests

response = requests.get('https://www.12306.cn', cert=('/path/server.crt', '/path/key'))
print(response.status_code)

代理设置

import requests

proxies = {
  "http": "http://127.0.0.1:9743",
  "https": "https://127.0.0.1:9743",
}

response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

import requests

proxies = {
    "http": "http://user:[email protected]:9743/",
}
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

pip3 install 'requests[socks]'

import requests

proxies = {
    'http': 'socks5://127.0.0.1:9742',
    'https': 'socks5://127.0.0.1:9742'
}
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

超时设置

import requests
from requests.exceptions import ReadTimeout
try:
    response = requests.get("http://httpbin.org/get", timeout = 0.5)
    print(response.status_code)
except ReadTimeout:
    print('Timeout')

认证设置

import requests
from requests.auth import HTTPBasicAuth

r = requests.get('http://120.27.34.24:9001', auth=HTTPBasicAuth('user', '123'))
print(r.status_code)

import requests

r = requests.get('http://120.27.34.24:9001', auth=('user', '123'))
print(r.status_code)

异常处理

import requests
from requests.exceptions import ReadTimeout, ConnectionError, RequestException
try:
    response = requests.get("http://httpbin.org/get", timeout = 0.5)
    print(response.status_code)
except ReadTimeout:
    print('Timeout')
except ConnectionError:
    print('Connection error')
except RequestException:
    print('Error')

Connection error

Urllib库的使用

urllib.urlopen

get请求

import urllib.request
response = urllib.request.urlopen('http://asahii.cn')
print(response.read().decode('utf-8'))

post请求

import urllib.parse
import urllib.request

data = bytes(urllib.parse.urlencode({'word':'hello'}), encoding='utf8')
response = urllib.request.urlopen('http://httpbin.org/post', data=data)
print(response.read().decode('utf-8'))

{
  "args": {}, 
  "data": "", 
  "files": {}, 
  "form": {
    "word": "hello"
  }, 
  "headers": {
    "Accept-Encoding": "identity", 
    "Connection": "close", 
    "Content-Length": "10", 
    "Content-Type": "application/x-www-form-urlencoded", 
    "Host": "httpbin.org", 
    "User-Agent": "Python-urllib/3.6"
  }, 
  "json": null, 
  "origin": "14.154.29.216", 
  "url": "http://httpbin.org/post"
}

超时时限设置。超过此值将抛出异常。

import urllib.request

response = urllib.request.urlopen('http://httpbin.org/get?data=haha', timeout=1)
print(response.read().decode('utf-8'))

{
  "args": {
    "data": "haha"
  }, 
  "headers": {
    "Accept-Encoding": "identity", 
    "Connection": "close", 
    "Host": "httpbin.org", 
    "User-Agent": "Python-urllib/3.6"
  }, 
  "origin": "14.154.29.216", 
  "url": "http://httpbin.org/get?data=haha"
}

捕捉异常

import socket
import urllib.request
import urllib.error

try:
    response = urllib.request.urlopen('http://httpbin.org/get', timeout=0.1)
except urllib.error.URLError as e:
    if isinstance(e.reason, socket.timeout):
        print('Time Out')

Time Out

响应

响应类型

import urllib.request

resp = urllib.request.urlopen('http://asahii.cn')
print(type(resp))

#resp = urllib.request.urlopen('https://www.python.org')
#print(type(resp))

print(resp.status)
print(resp.getheaders())
print(resp.getheader('Server'))

200
[('Server', 'GitHub.com'), ('Content-Type', 'text/html; charset=utf-8'), ('Last-Modified', 'Sat, 20 Jan 2018 04:10:07 GMT'), ('Access-Control-Allow-Origin', '*'), ('Expires', 'Mon, 22 Jan 2018 13:32:43 GMT'), ('Cache-Control', 'max-age=600'), ('X-GitHub-Request-Id', '71A8:11832:91183A:9A71F6:5A65E5A3'), ('Content-Length', '106'), ('Accept-Ranges', 'bytes'), ('Date', 'Mon, 22 Jan 2018 14:26:04 GMT'), ('Via', '1.1 varnish'), ('Age', '480'), ('Connection', 'close'), ('X-Served-By', 'cache-hnd18748-HND'), ('X-Cache', 'HIT'), ('X-Cache-Hits', '1'), ('X-Timer', 'S1516631164.467386,VS0,VE0'), ('Vary', 'Accept-Encoding'), ('X-Fastly-Request-ID', 'f3adc99bea78d082bc4447a4a04f427731a40dad')]
GitHub.com

Request

构造请求，包括增添一些请求头部信息等。

from urllib import request, parse

req = urllib.request.Request('http://asahii.cn')
resp = urllib.request.urlopen(req)
print(resp.read().decode('utf-8'))

##########################   分隔线   ##########################
url = 'http://httpbin.org/post'
headers = {
    'User-Agent':'Mozilla/4.0(compatible;MSIE 5.5;Windows NT)',
    'Host':'httpbin.org'
}
dict = {
    'name':'Germey'
}
data = bytes(parse.urlencode(dict), encoding='utf8')
req = request.Request(url=url, data=data, headers=headers, method='POST')
resp = request.urlopen(req)
print(resp.read().decode('utf-8'))

    


{
  "args": {}, 
  "data": "", 
  "files": {}, 
  "form": {
    "name": "Germey"
  }, 
  "headers": {
    "Accept-Encoding": "identity", 
    "Connection": "close", 
    "Content-Length": "11", 
    "Content-Type": "application/x-www-form-urlencoded", 
    "Host": "httpbin.org", 
    "User-Agent": "Mozilla/4.0(compatible;MSIE 5.5;Windows NT)"
  }, 
  "json": null, 
  "origin": "14.154.29.0", 
  "url": "http://httpbin.org/post"
}

from urllib import request,parse

url = 'http://httpbin.org/post'
dict = {
    'name':'China'
}
data = bytes(parse.urlencode(dict), encoding='utf8')
req = request.Request(url=url, data=data, method='POST')
req.add_header('User-Agent', 'Mozilla/4.0(compatible;MSIE 5.5;Windows NT)')
resp = request.urlopen(req)
print(resp.read().decode('utf-8'))

{
  "args": {}, 
  "data": "", 
  "files": {}, 
  "form": {
    "name": "China"
  }, 
  "headers": {
    "Accept-Encoding": "identity", 
    "Connection": "close", 
    "Content-Length": "10", 
    "Content-Type": "application/x-www-form-urlencoded", 
    "Host": "httpbin.org", 
    "User-Agent": "Mozilla/4.0(compatible;MSIE 5.5;Windows NT)"
  }, 
  "json": null, 
  "origin": "14.154.28.26", 
  "url": "http://httpbin.org/post"
}

Handler

设置代理。可以通过来回切换代理，以防止服务器禁用我们的IP。

import urllib.request

proxy_handler = urllib.request.ProxyHandler({
    'http':'http://127.0.0.1:9743',
    'https':'https://127.0.0.1:9743'
})

opener = urllib.request.build_opener(proxy_handler)
resp = opener.open('http://www.baidu.com')
print(resp.read())

Cookie相关操作

用来维持登录状态。可以在遇到需要登录的网站使用。

# 获取cookie
import http.cookiejar, urllib.request
cookie = http.cookiejar.CookieJar()
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
resp = opener.open('http://www.baidu.com')
for item in cookie:
    print(item.name+"="+item.value)

BAIDUID=417382BEB774A45EA7FC2C374C846E04:FG=1
BIDUPSID=417382BEB774A45EA7FC2C374C846E04
H_PS_PSSID=25639_1446_21107_20930
PSTM=1516632429
BDSVRTM=0
BD_HOME=0

保存cookie到本地文件中

import http.cookiejar, urllib.request
filename = "cookie.txt"
cookie = http.cookiejar.MozillaCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
resp = opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True, ignore_expires=True)

另一种cookie保存格式

import http.cookiejar, urllib.request
filename = "cookie.txt"
cookie = http.cookiejar.LWPCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
resp = opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True, ignore_expires=True)

加载本地cookie到请求中去。用什么样的方式存cookie，就用什么样的方式去读。

import http.cookiejar, urllib.request
cookie = http.cookiejar.LWPCookieJar()
cookie.load('cookie.txt', ignore_discard=True, ignore_expires=True)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
resp = opener.open('http://httpbin.org/get')
print(resp.read().decode('utf8'))

{
  "args": {}, 
  "headers": {
    "Accept-Encoding": "identity", 
    "Connection": "close", 
    "Host": "httpbin.org", 
    "User-Agent": "Python-urllib/3.6"
  }, 
  "origin": "14.154.29.0", 
  "url": "http://httpbin.org/get"
}

页面请求时的异常处理

from urllib import request, error
try:
    resp = request.urlopen('http://asahii.cn/index.htm')
except error.URLError as e:
    print(e.reason)#可考虑进行重拾

Not Found

详细的错误类型

from urllib import request, error
try:
    resp = request.urlopen('http://asahii.cn/index.htm')
except error.HTTPError as ee:
    print(ee.reason, ee.code, ee.headers, sep='\n')
except error.URLError as e:
    print(e.reason)

Not Found
404
Server: GitHub.com
Content-Type: text/html; charset=utf-8
ETag: "5a62c123-215e"
Access-Control-Allow-Origin: *
X-GitHub-Request-Id: F758:1D9CC:916D4F:9B5FD5:5A65FE22
Content-Length: 8542
Accept-Ranges: bytes
Date: Mon, 22 Jan 2018 15:09:43 GMT
Via: 1.1 varnish
Age: 148
Connection: close
X-Served-By: cache-hnd18733-HND
X-Cache: HIT
X-Cache-Hits: 1
X-Timer: S1516633784.646920,VS0,VE0
Vary: Accept-Encoding
X-Fastly-Request-ID: fb6b42a4706a17c3de8bd318b76be3513b68c49b

加上原因判断

import socket
from urllib import request, error
try:
    resp = request.urlopen('http://asahii.cn/index.html', timeout=0.01)
except error.URLError as e:
    print(type(e.reason))
    if isinstance(e.reason, socket.timeout):
        print('TIME OUT')

TIME OUT

网页解析

解析URL

from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment')
print(type(result), result, sep='\n')

result = urlparse('www.baidu.com/index.html;user?id=5#comment', scheme='https')
print(result)

result = urlparse('http://www.baidu.com/index.html;user?id=5#comment', scheme='https')
print(result)

result = urlparse('http://www.baidu.com/index.html;user?id=5#comment', allow_fragments=False)
print(result)

result = urlparse('http://www.baidu.com/index.html#comment', allow_fragments=False)
print(result)

ParseResult(scheme='http', netloc='www.baidu.com', path='/index.html', params='user', query='id=5', fragment='comment')
ParseResult(scheme='https', netloc='', path='www.baidu.com/index.html', params='user', query='id=5', fragment='comment')
ParseResult(scheme='http', netloc='www.baidu.com', path='/index.html', params='user', query='id=5', fragment='comment')
ParseResult(scheme='http', netloc='www.baidu.com', path='/index.html', params='user', query='id=5#comment', fragment='')
ParseResult(scheme='http', netloc='www.baidu.com', path='/index.html#comment', params='', query='', fragment='')

URL拼装

from urllib.parse import urlunparse
data=['http', 'www.baidu.com', 'index.html', 'user', 'a=6', 'comment']
print(urlunparse(data))

http://www.baidu.com/index.html;user?a=6#comment

from urllib.parse import urlencode
params = {
    'name':'germey',
    'age':22
}
base_url = 'http://www.baidu.com?'
url = base_url+urlencode(params)
print(url)

http://www.baidu.com?name=germey&age=22