python解析_使用python解析网页内容 | DannyWu博客

class GetWebResult():

def __init__(self):

jobs_id = 139366

self.jobs_url = 'http://cbsp-wm-bl01/icase/api/rest/test/jobresults/?ids=%d' % jobs_id@staticmethod

def get_soup(url):

headers = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'}

req = urllib2.Request(url, headers=headers)

f = urllib2.urlopen(req, timeout=10)

html = f.read()

f.close()

return htmldef main(self):

save_path = os.path.join(os.getcwd(), 'JobResult.xls')

string_of_results = self.get_soup(self.jobs_url)

tmp = string_of_results.replace('null', "\"null\"").replace('true', "\"true\"").replace('false', "\"false\"")

results = eval(tmp)[0].get('results')

list_of_dict_result = []

for result in results:

list_of_dict_result.append(self.convert_result(result))

key_list = ['Name', 'Image', 'Subsystem', 'Functionality', 'Objective', 'Assumptions', 'Steps', 'Tickets', 'Metrics', 'Notes', 'Result']

xls = Excel(save_path)

xls.insert_sheet(sheet_name='results', list_dict=list_of_dict_result, list_key=key_list)

@staticmethod

def convert_result(dict):

dict_result = {}

case = dict.get('case')

dict_result['Tickets'] = dict.get('tickets')

dict_result['Metrics'] = dict.get('metrics')

dict_result['Notes'] = dict.get('notes')

dict_result['Result'] = dict.get('result')

dict_result['Name'] = case.get('name')

dict_result['Image'] = case.get('image').get('name')

dict_result['Subsystem'] = case.get('taxonomy').get('subsystem').get('name')

dict_result['Functionality'] = case.get('taxonomy').get('functional_area').get('name')

dict_result['Objective'] = case.get('objective').decode('utf-8')

dict_result['Assumptions'] = case.get('assumptions')

dict_result['Steps'] = case.get('steps').decode('utf-8')

return dict_result