Python利用Requests庫寫爬蟲（一）

#-*- coding:utf-8 -*-

import requests
url = ''
r = requests.get(url)
print r.text

#-*- coding:utf-8 -*-

import requests
url = ''
payload = 
r = requests.get(url, params=payload)
print r.text

#-*- coding:utf-8 -*-

import requests
url1 = ''#登陸位址
url2 = ""#需要登陸才能訪問的位址
data=
"accept-encoding":"gzip",
"accept-language":"zh-cn,zh;q=0.8",
"referer":"",
}res1 = requests.post(url1, data=data, headers=headers)
res2 = requests.get(url2, cookies=res1.cookies, headers=headers)
print res2.content#獲得二進位制響應內容
print res2.raw#獲得原始響應內容,需要stream=true
print res2.raw.read(50)
print type(res2.text)#返回解碼成unicode的內容
print res2.url
print res2.history#追蹤重定向
print res2.cookies
print res2.cookies['example_cookie_name']
print res2.headers
print res2.headers['content-type']
print res2.headers.get('content-type')
print res2.json#講返回內容編碼為json
print res2.encoding#返回內容編碼
print res2.status_code#返回http狀態碼
print res2.raise_for_status()#返回錯誤狀態碼

#-*- coding:utf-8 -*-

import requests
s = requests.session()
url1 = ''#登陸位址
url2 = ""#需要登陸才能訪問的位址
data=
"accept-encoding":"gzip",
"accept-language":"zh-cn,zh;q=0.8",
"referer":"",
}prepped1 = requests.request('post', url1,
data=data,
headers=headers
).prepare()
s.send(prepped1)
'''也可以這樣寫
res = requests.request('post', url1,
data=data,
headers=headers
)prepared = s.prepare_request(res)
# do something with prepped.body
# do something with prepped.headers
s.send(prepared)
'''prepare2 = requests.request('post', url2,
headers=headers
).prepare()
res2 = s.send(prepare2)
print res2.content

#-*- coding:utf-8 -*-

import requests
s = requests.session()
url1 = ''#登陸位址
url2 = ""#需要登陸才能訪問的頁面位址
data=
"accept-encoding":"gzip",
"accept-language":"zh-cn,zh;q=0.8",
"referer":"",
}res1 = s.post(url1, data=data)
res2 = s.post(url2)
print(resp2.content)

>>> r = requests.put("")

>>> r = requests.delete("")
>>> r = requests.head("")
>>> r = requests.options("")

unicodeencodeerror:'gbk' codec can't encode character u'\xbb' in   

position 23460: illegal multibyte sequence

1、unicode是編碼還是解碼

unicodeencodeerror

2、用了什麼編碼

'gbk' codec can't encode character

確定當前字串，比如

#-*- coding:utf-8 -*-

import requests
url = ''
r = requests.get(url)
print r.encoding
>utf-8

print r.text.encode('utf-8')

Python爬蟲 Request模組

文章說明了request模組的意義，且強調了request模組使用更加方便。接下來介紹幾種常用的request操作，並且會在後續補充說明一些特定用法。匯入檔案 import requests一 請求 右邊為請求語句，返回值為response回應 r requests.get r requests.p...

python爬蟲利器 request庫

request庫比urllib2庫更為高階，因為其功能更強大，更易於使用。使用該庫可以十分方便我們的抓取。基本請求 r requests.get r requests.post r requests.put r requests.delete r requests.head r requests.o...

Python 使用request傳送http請求

requests.get headers response requests.post login headers headers,data data response requests.post login allow redirects false 注 若不禁止重定向，則當響應是302時，req...