requests实例

# &＃61;&＃61;&＃61;爬取京东
url &＃61; &＃39;&＃39;
try:r &＃61; requests.get(url)r.raise_for_status()r.encoding &＃61; r.apparent_encodingprint(r.text[:1000]) # 展示前一千字节的数据
except:print(&＃39;爬取失败&＃39;)# &＃61;&＃61;&＃61;爬取亚马逊
url &＃61; &＃39;&＃39;
try:kv &＃61; {&＃39;user-agent&＃39;:&＃39;Mozilla/5.0&＃39;}r &＃61; requests.get(url, headers&＃61;kv) # 浏览器伪装 Chrome/51.0.2704.63 Safari/537.36r.raise_for_status()r.encoding &＃61; r.apparent_encodingprint(r.text[1000:2000])
except:print(&＃39;爬取失败&＃39;)# &＃61;&＃61;&＃61;百度搜索
# 百度的关键词接口&＃xff1a; http://www.baidu.com/s?wd&＃61;keyword
keyword &＃61; &＃39;python&＃39; # keyword即要搜索的词
try:kv &＃61; {&＃39;wd&＃39;: keyword}r &＃61; requests.get(&＃39;http://www.baidu.com/s&＃39;, params&＃61;kv)print(r.request.url)r.raise_for_status()print(len(r.text)) # 输出返回文本的长度
except:print(&＃39;爬取失败&＃39;)# &＃61;&＃61;&＃61;360搜索
# 360的关键词接口&＃xff1a; http://www.so.com/s?q&＃61;keyword
keyword &＃61; &＃39;python&＃39;
try:kv &＃61; {&＃39;q&＃39;: keyword}r &＃61; requests.get(&＃39;http://www.so.com/s&＃39;, params&＃61;kv)print(r.request.url)r.raise_for_status()print(len(r.text)) # 输出返回文本的长度
except:print(&＃39;爬取失败&＃39;)# &＃61;&＃61;&＃61;网络图片爬取
url &＃61; &＃39;&＃39; # 图片地址
root &＃61; &＃39;D://PICS//&＃39; # 硬盘地址
path &＃61; root &＃43; url.split(&＃39;/&＃39;)[-1] # 硬盘地址&＃43;图片地址最后一个以 / 为分割的名字
try:if not os.path.exists(root):os.mkdir(root) # 数字模式创建目录if not os.path.exists(path):r &＃61; requests.get(url)with open(path, &＃39;wb&＃39;) as f:f.write(r.content)f.close()print(&＃39;文件保存成功&＃39;)else:print(&＃39;文件已存在&＃39;)
except:print(&＃39;爬取失败&＃39;)# &＃61;&＃61;&＃61;IP地址查询
url &＃61; &＃39;http://m.ip138.com/ip.asp?ip&＃61;ipaddress&＃39;
try:r &＃61; requests.get(url &＃43; &＃39;IP&＃39;)r.raise_for_status()r.encoding &＃61; r.apparent_encodingprint(r.text[-500:])
except:print(&＃39;爬取失败&＃39;)