爬蟲中什麽是requests
阿新 • • 發佈:2018-10-21
header use lan os.path 上傳 lxml main pro inf
print(response.text) #響應的信息
print(response.headers) #獲取響應頭
print(response.status_code) #響應狀態碼
print(response.encoding) #響應的編碼
print(response.cookies) #獲取cookies信息
帶參數GET請求
data = {
‘name‘:‘abc‘,
‘‘‘‘‘‘
}
response = requests.get(url=‘http://www.baidu.com‘,params=data)
解析json
import requests response = requests.get(url=‘http://www.baidu.com‘) print(response.json())
獲取二進制數據
import requests
response = requests.get(url=‘http://www.baidu.com‘)
print(response.content)
高級操作
文件上傳
import requests
flies = {
‘flies‘:open(‘XXX‘,‘rb‘)
}
response = requests.post(url=‘http://www.baidu.com‘,flies=flies)
print(response.content)
會話維持 (模擬登陸)
import requests s = requests.Session() s.get(‘http://httpbin.org/cookies/set/number/123456789‘) response = s.get(‘http://httpbin.org/cookies‘) print(response.text) { "cookies": { "number": "123456789" } }
證書驗證
import requests
import urllib3
url = ‘https://www.biqudu.com/43_43821/2520338.html‘
urllib3.disable_warnings() #關閉證書後再把警告提示關閉
response = requests.get(url=url,verify=False)
print(response.text)
代理認證
url = ‘https://www.biqudu.com/43_43821/2520338.html‘ proxies = { ‘http‘:‘http://127.0.0.2‘, ‘https‘:‘http://user:[email protected]‘, #帶密碼的代理 } response = requests.get(url=url,proxies=proxies) print(response.text) ****
請求超時處理
import requests
from requests.exceptions import ReadTimeout #導入錯誤模塊
url = ‘https://www.taobao.com‘
try:
response = requests.get(url=url,timeout=0.1) #限制請求時間
print(response.status_code)
except ReadTimeout:
print(‘請求超時‘)
認證設置
#有的網站打開的瞬間就需要密碼認證
import requests
from requests.auth import HTTPBasicAuth
url = ‘https://www.taobao.com‘
response = requests.get(url=url,auth=(‘user‘,‘pwd‘))
print(response.status_code)
1,筆趣閣小說(入門級爬取文本信息)
抓取筆趣閣小說:排行榜單的小說總榜
1.請求初始url,獲取網頁源碼
2.解析網頁源碼,得到文本內容
3.將小說全部章節名存入txt文件中
from lxml import etree
import requests
url = ‘http://www.biqiuge.com/paihangbang‘
response = requests.get(url)
response.encoding = response.apparent_encoding
html = etree.HTML(response.text)
info = html.xpath("//div[@class=‘block bd‘][1]/ul[@class=‘tli‘]/li/a")
for i in info:
title = i.xpath("./text()")[0]
urls =i.xpath("./@href")[0]
urls1 = ‘http://www.biqiuge.com‘+urls
with open(title+‘.txt‘,‘w+‘,encoding=‘utf-8‘) as f:
response1 = requests.get(url=urls1)
response1.encoding = response1.apparent_encoding
html = etree.HTML(response1.text)
info = html.xpath("//div[@class=‘listmain‘]/dl/dd/a/text()")[6:]
for i in info:
f.write(i.strip()+‘\n‘)
print(title+"------寫入成功")
------------------------------------------------------
判斷路徑是否存在,自動創建!!!
if not os.path.exists(title):
os.mkdir(title)
path = os.path.join(title,title1)
if not os.path.exists(path):
os.mkdir(path)
with open(path+ ‘\\‘ + title2 +‘.txt‘, ‘w+‘, encoding=‘utf-8‘) as f:
for con in contents:
f.write(con.strip() + ‘\n‘)
print(title +‘---‘+ title1 +‘---‘+ title2 + ‘---寫入成功‘)
2,崔慶才博客(偽造頭信息爬取策略)
from lxml import etree
import requests
n = 0
with open(‘cuijincai.txt‘, ‘w+‘, encoding=‘utf-8‘) as f:
for i in range(1,10):
url = ‘https://cuiqingcai.com/category/technique/python/page/‘+str(i)
#這裏的循環,該網站是動態顯示,可以在f12/network中XHR中查到該鏈接url。
headers = {
Referer: https://cuiqingcai.com/category/technique/python
‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36‘
}
#部分網站設置反爬機制,可以為請求頭設置 信息
response = requests.get(url=url,headers=headers)
html = etree.HTML(response.text)
all_div = html.xpath("//article[@class=‘excerpt‘]")
for div in all_div:
title = div.xpath("./header/h2/a/text()")[0] #當前路徑下的標題信息
author = div.xpath("./p[@class=‘auth-span‘]/span[@class=‘muted‘][1]/a/text()")[0]
time = div.xpath("./p[@class=‘auth-span‘]/span[@class=‘muted‘][2]/text()")[0]
liulanshu = div.xpath("./p[@class=‘auth-span‘]/span[@class=‘muted‘][3]/text()")[0]
pinlun = div.xpath("./p[@class=‘auth-span‘]/span[@class=‘muted‘][4]/a/text()")[0]
like = div.xpath("./p[@class=‘auth-span‘]/span[@class=‘muted‘][5]/a[@id=‘Addlike‘]/span[@class=‘count‘]/text()")[0]+‘喜歡‘
n += 1
f.write("第{}條\t{}\t{}\t{}\t{}\t{}\t{}\n".format(n,title,author,time,liulanshu,pinlun,like))
User Agent中文名為用戶代理,簡稱 UA,它是一個特殊字符串頭,使得服務器能夠識別客戶使用的操作系統及版本、CPU 類型、瀏覽器及版本、
瀏覽器渲染引擎、瀏覽器語言、瀏覽器插件等。
HTTP Referer是header的一部分,當瀏覽器向web服務器發送請求的時候,一般會帶上Referer,告訴服務器我是從哪個頁面鏈接過來的,
服務器基此可以獲得一些信息用於處理。
https://www.liaoxuefeng.com 該網站設置反爬,可以用上面設置頭信息爬取
爬蟲中什麽是requests