javascript - 抓取页面以获取编码的 javascript 链接
问题描述
我正在处理一项任务,我必须使用 python 请求库从网页获取详细信息。我已经成功地从页面获取了详细信息,但它有一个“显示详细信息”按钮,它使用 ajax 调用获取更多详细信息,现在我还需要获取这些额外的详细信息。谁能帮我这样做?这是网站的链接:- http://ipindiaonline.gov.in/tmrpublicsearch/frmmain.aspx
和网站的屏幕截图:
这是我制作的代码。
from bs4 import BeautifulSoup
import requests,json
def returnJson(wordmark, page_class):
url = "http://ipindiaonline.gov.in/tmrpublicsearch/frmmain.aspx"
r_init = requests.get(url)
soup = BeautifulSoup(r_init.text, 'html.parser')
event_validation = soup.find("input", attrs={"name" : "__EVENTVALIDATION"})['value']
view_state = soup.find("input", attrs={"name" : "__VIEWSTATE"})['value']
search_type = 'WM'
postdata = {
'ctl00$ContentPlaceHolder1$DDLFilter' : '0',
'ctl00$ContentPlaceHolder1$DDLSearchType' : search_type,
'ctl00$ContentPlaceHolder1$TBWordmark' : wordmark,
'ctl00$ContentPlaceHolder1$TBClass' : page_class,
'__EVENTVALIDATION' : event_validation,
"__EVENTTARGET" : "ctl00$ContentPlaceHolder1$BtnSearch",
"__VIEWSTATE" : view_state,
}
r = requests.post(url, data=postdata)
return r
def scraping(r):
soup = BeautifulSoup(r.text, 'html.parser')
counter=len(soup.findAll('tr',attrs={'class':'row'}))
counter+=len(soup.findAll('tr',attrs={'class':'alt'}))
wordmark_idvalue='ContentPlaceHolder1_MGVSearchResult_lblsimiliarmark_'
proprietor_idvalue='ContentPlaceHolder1_MGVSearchResult_LblVProprietorName_'
applicationno_idvalue='ContentPlaceHolder1_MGVSearchResult_lblapplicationnumber_'
class_idvalue='ContentPlaceHolder1_MGVSearchResult_lblsearchclass_'
status_idvalue='ContentPlaceHolder1_MGVSearchResult_Label6_'
words_list=[]
for i in range(0,counter):
words_dict={}
row=soup.find('span',attrs={'id':(wordmark_idvalue+str(i))})
words_dict['Wordmark']=row.text
row=soup.find('span',attrs={'id':(proprietor_idvalue+str(i))})
words_dict['Proprietor']=row.text
row=soup.find('span',attrs={'id':(applicationno_idvalue+str(i))})
words_dict['Application Number']=row.text
row=soup.find('span',attrs={'id':(class_idvalue+str(i))})
words_dict['Class ']=row.text
row=soup.find('span',attrs={'id':(status_idvalue+str(i))})
words_dict['Status']=row.text
words_list.append(words_dict)
return words_list
def showDetails(wordmark, page_class):
if(len(wordmark)>2 and page_class.isalnum()==1):
var=json.dumps(scraping(returnJson(wordmark, page_class)))
return var
else:
print("Please Enter Valid Parameters\n")
showDetails('AIWA','2')
解决方案
您需要使用第一个 POST 请求中的信息创建另一个 POST 请求。下面显示了如何Goods & Services Description
从返回的数据中提取 :
from operator import itemgetter
from bs4 import BeautifulSoup
import requests,json
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.47 Safari/537.36'}
def get_input_value(soup, name):
return soup.find("input", attrs={"name" : name})['value']
def returnJson(wordmark, page_class):
url = "http://ipindiaonline.gov.in/tmrpublicsearch/frmmain.aspx"
r_init = requests.get(url)
soup = BeautifulSoup(r_init.text, 'html.parser')
postdata = {
"ctl00$ContentPlaceHolder1$DDLFilter" : "0",
"ctl00$ContentPlaceHolder1$DDLSearchType" : "WM",
"ctl00$ContentPlaceHolder1$TBWordmark" : wordmark,
"ctl00$ContentPlaceHolder1$TBClass" : page_class,
"__EVENTVALIDATION" : get_input_value(soup, "__EVENTVALIDATION"),
"__EVENTTARGET" : "ctl00$ContentPlaceHolder1$BtnSearch",
"__VIEWSTATE" : get_input_value(soup, "__VIEWSTATE"),
}
r = requests.post(url, headers=headers, data=postdata)
return r
def scraping(r):
soup = BeautifulSoup(r.content, 'html.parser')
counter = len(soup.find_all('tr', attrs={'class':'row'}))
counter += len(soup.find_all('tr', attrs={'class':'alt'}))
words_list = []
fields = [
("Wordmark", "ContentPlaceHolder1_MGVSearchResult_lblsimiliarmark_{}"),
("Proprietor", "ContentPlaceHolder1_MGVSearchResult_LblVProprietorName_{}"),
("Application Number", "ContentPlaceHolder1_MGVSearchResult_lblapplicationnumber_{}"),
("Class", "ContentPlaceHolder1_MGVSearchResult_lblsearchclass_{}"),
("Status", "ContentPlaceHolder1_MGVSearchResult_Label6_{}"),
]
for index in range(0, counter):
words_dict = {}
for key, field in fields:
words_dict[key] = soup.find('span', attrs={'id' : field.format(index)}).text
print("Wordmark: {}".format(words_dict["Wordmark"]))
# Construct a POST request for the Show Details panel
# Locate matching 'Show details' link
span = soup.find('span', attrs={'id' : fields[0][1].format(index)})
a = span.find_next('a', class_='LnkshowDetails')
lnk_show_details = a['href'].split("'")[1]
data = {
"__EVENTTARGET" : lnk_show_details,
"__VIEWSTATE" : get_input_value(soup, "__VIEWSTATE"),
"__VIEWSTATEENCRYPTED" : "",
"__EVENTVALIDATION" : get_input_value(soup, "__EVENTVALIDATION"),
"__ASYNCPOST" : "true",
}
url = "http://ipindiaonline.gov.in/tmrpublicsearch" + soup.form["action"].strip(".")
r_details = requests.post(url, headers=headers, data=data)
html = b''.join(itemgetter(7, 8)(r_details.content.split(b"|")))
soup_details = BeautifulSoup(html, "html.parser")
details = {}
for tr in soup_details.find_all('tr'):
row = [td.text for td in tr.find_all('td')] # Note: Journal No and Used since would need more work
details[row[0]] = row[1]
# Copy description
desc = 'Goods & Services Description'
words_dict[desc] = details[desc]
words_list.append(words_dict)
return words_list
def showDetails(wordmark, page_class):
if len(wordmark) > 2 and page_class.isalnum() == 1:
var = json.dumps(scraping(returnJson(wordmark, page_class)))
return var
else:
print("Please Enter Valid Parameters\n")
print(showDetails('AIWA','2'))
这将显示:
Wordmark: AIWA
Wordmark: AIWACEM
Wordmark: AIWAPRIME (LABEL)
[{"Wordmark": "AIWA", "Proprietor": "AIWA CO. LTD.", "Application Number": "683935", "Class": "2", "Status": "Registered", "Goods & Services Description": "PAINTS, VARNISHES, LACQUERS, PRESERVATIVES AGAINST RUST AND AGAINST DESTRIORATION OF WOOD, COLOURING MATTERS, DYESTUFFS, MORDANTS, NATURAL RESINS, METALS IN FOIL AND POWDER FROM FOR PAINTERS AND DECORATORS."}, {"Wordmark": "AIWACEM ", "Proprietor": "AMITA B. MEHTA", "Application Number": "1108415", "Class": "2", "Status": "Registered", "Goods & Services Description": "waterproof cement paint."}, {"Wordmark": "AIWAPRIME (LABEL)", "Proprietor": "AMITA B. MEHTA", "Application Number": "1165809", "Class": "2", "Status": "Registered", "Goods & Services Description": "WATER BASED CEMENT PRIMER INCLUDED IN CLASS 2."}]
|
注意:返回的数据包含以字符分隔的其他字段。详细信息的 HTML 也恰好包含此字符,因此有必要提取字段7
并8
仅获取 HTML。
推荐阅读
- ios - UISearchBarSearchField 背景视图颜色
- amazon-web-services - 我可以在没有网关 API 的情况下直接调用 AWS Lambda 吗?
- java - 使用 HTTPs 调用 GET 中的 @RequestParam 始终为空
- visual-studio - VS 2010 无法连接 AzureDevops server 2019 中的项目
- mysql - 如何使用 MySQL 获得类似数据透视表的结果
- angular - 升级到 Angular 8.3.5 后,Angular 应用程序不加载应用程序模块/组件
- python - 如何将变量作为 url 的一部分?
- python-2.7 - 从 API 触发 ansible playbook 并在后台运行它们
- django - 来自 ListBox 的数据发布未呈现到数据库
- c# - 如何更新注释的内容