def resolver():
import shared
r = shared.r
r.GET(shared.URL)
from htmlparser import between, unescape
from urllib import unquote
shared.filename = between(r.Page, '<title>', '</title>')+'.flv'
watch = between(r.Page, '<object', '</object>', include=True).replace('>','>\n')
player = between(watch, 'name="movie" value="', '"')
flashvars = between(watch, 'name="flashvars" value="', '"')
def fmt_stream_map(var):
v = var.split('&')[0] # first parameter, discard "quality=medium" etc.
urls = unquote(v)[4:] # without "url="
return urls
_flashvars = flashvars.replace('&',"'").split("'")
for var in _flashvars:
s = var.split('=')
key = s[0]
if key == 'url_encoded_fmt_stream_map': # that's the interesting part
_values = unquote(s[1]).split(',')
values = [fmt_stream_map(_values[i]) for i in range(len(_values))]
print str(len(values))+' URLs:\n'+str(values)
try:
shared.URL = values[0] # get the first URL in the list
except:
shared.URL = ''
def extractSeasons(self): selectSeason = between(self.page, '<SELECT name="season"', '</SELECT>') i = 0 self.seasons = [] season = between(selectSeason, '<OPTION value="', '"') while season != '': self.seasons.append(season.strip()) i += 1 season = between(selectSeason, '<OPTION value="', '"', skip=i) return self.seasons
def extractEpisodes(self, season):
allEpisodes = between(self.page, '<FORM name="episodeform'+season+'">', '</FORM>')
i = 0
self.episodes = {}
episode = between(allEpisodes, '>Episode ', '</OPTION')
while episode != '':
pageURL = between(allEpisodes, '<OPTION value="', '"', skip=i)
i += 1
if pageURL != '':
self.episodes[episode] = completeURL(pageURL)
episode = between(allEpisodes, '>Episode ', '</OPTION', skip=i)
return self.episodes
def extractVideoLink(self, page=None):
if page is None:
page = self.page
url = between( between(page, 'question.png', 'IMDB Rating'), '<a target="_blank" href="', '"' )
if url == '':
url = between(page, '<div id="emptydiv"><iframe src="', '"')
url = url.replace('.com/embed/', '.com/file/')
# movie splitted into several video files
if 'teil1_aktiv.png' in page:
print 'part 2 ...'
client = HttpClient()
client.GET( between( between(page, 'teil1_aktiv.png', 'teil2_inaktiv.png'), '<a href="', '"') )
url = [url, extractVideoLink(client.Page)]
del client
return url
def parseXML(xml):
authors = []
skip = 1
a = between(xml, '<LastName>', '</LastName>', skip)
while a != '':
if a in unrecognized_authors.keys():
print 'Warning: changing problematic author name '+a+' to '+unrecognized_authors[a]
a = unrecognized_authors[a]
authors.append(a.replace(' ','').replace('-',''))
skip += 1
a = between(xml, '<LastName>', '</LastName>', skip)
title = between(xml, '<ArticleTitle>', '</ArticleTitle>').strip('\t .')
journal = between(xml, '<ISOAbbreviation>', '</ISOAbbreviation>')
year = between(between(xml, '<PubDate>', '</PubDate>'), '<Year>', '</Year>')
doi = between(xml, '<ArticleId IdType="doi">', '</ArticleId>')
url = 'http://www.ncbi.nlm.nih.gov/pubmed/'+ID
bibtex = '@article{'+authors[0]+year+',\n'
bibtex += '\ttitle = "'+title+'",\n'
bibtex += '\tauthor = "{'+'} and {'.join(authors)+'}",\n'
bibtex += '\tjournal = "'+journal+'",\n'
bibtex += '\tyear = '+year+',\n'
bibtex += '\tdoi = {'+doi+'},\n'
bibtex += '\turl = {'+url+'}\n'
bibtex += '}\n\n'
return bibtex
def resolver():
import shared
r = shared.r
r.GET(shared.URL)
from htmlparser import between
s = shared.URL.split("/")
MyVideoID = s[len(s)-2]
img_src = between(r.Page, "<img id='i"+MyVideoID+"' src='", "'").replace("http://","")
folder = "/".join( img_src.split("/")[1:4] )
shared.URL = "http://is3.myvideo.de/"+folder+"/"+MyVideoID+".flv"
def extractHosters(self, URL=None):
global client
if URL != None:
client.GET(URL)
self.page = str(client.Page)
self.hosters = {}
i = 0
tr = between(self.page, '<tr id="tablemoviesindex2"', "</tr>")
while tr != '':
link = completeURL( between(tr, '<a href="', '"') )
if link != '':
m = Movie2kPage(link)
link = m.extractVideoLink()
del m
name = between( between(tr, '<td ', '</td>', skip=1), ' ', '</a>' )
self.hosters[name] = link
i += 1
tr = between(self.page, '<tr id="tablemoviesindex2"', "</tr>", skip=i)
return self.hosters
def downloadCitation(ID):
browser = HttpClient()
browser.GET('http://www.ncbi.nlm.nih.gov/pubmed/'+ID)
q = {}
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_SearchBar.SearchResourceList'] = 'pubmed'
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_SearchBar.Term'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_SearchBar.CurrDb'] = 'pubmed'
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_PageController.PreviousPageName'] = 'results'
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_DisplayBar.sPresentation'] = 'xml'
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_DisplayBar.FFormat'] = 'abstract'
q['email_format'] = 'abstract'
q['email_address'] = ''
q['email_subj'] = '1+selected+item%3A+'+ID+'+-+PubMed'
q['email_add_text'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_DisplayBar.FileFormat'] = 'abstract'
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_DisplayBar.LastPresentation'] = 'abstract'
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_DisplayBar.Presentation'] = 'xml'
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_DisplayBar.PageSize'] = '20'
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_DisplayBar.LastPageSize'] = '20'
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_DisplayBar.Sort'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_DisplayBar.LastSort'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_DisplayBar.FileSort'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_DisplayBar.Format'] = 'text'
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_DisplayBar.LastFormat'] = ''
q['CitationManagerStartIndex'] = '1'
q['CitationManagerCustomRange'] = 'false'
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_ResultsController.ResultCount'] = '1'
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_ResultsController.RunLastQuery'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.HistoryDisplay.Cmd'] = 'displaychanged'
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.EmailTab.EmailReport'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.EmailTab.EmailFormat'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.EmailTab.EmailCount'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.EmailTab.EmailStart'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.EmailTab.EmailSort'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.EmailTab.Email'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.EmailTab.EmailSubject'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.EmailTab.EmailText'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.EmailTab.EmailQueryKey'] = ''
q['EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.EmailTab.QueryDescription'] = ''
q['EntrezSystem2.PEntrez.DbConnector.Db'] = 'pubmed'
q['EntrezSystem2.PEntrez.DbConnector.LastDb'] = 'pubmed'
q['EntrezSystem2.PEntrez.DbConnector.Term'] = ''
q['EntrezSystem2.PEntrez.DbConnector.LastTabCmd'] = ''
q['EntrezSystem2.PEntrez.DbConnector.LastQueryKey'] = '1'
q['EntrezSystem2.PEntrez.DbConnector.IdsFromResult'] = ''
q['EntrezSystem2.PEntrez.DbConnector.LastIdsFromResult'] = ''
q['EntrezSystem2.PEntrez.DbConnector.LinkName'] = ''
q['EntrezSystem2.PEntrez.DbConnector.LinkReadableName'] = ''
q['EntrezSystem2.PEntrez.DbConnector.LinkSrcDb'] = ''
q['EntrezSystem2.PEntrez.DbConnector.Cmd'] = 'displaychanged'
q['EntrezSystem2.PEntrez.DbConnector.TabCmd'] = ''
q['EntrezSystem2.PEntrez.DbConnector.QueryKey'] = ''
q['p%24a'] = 'EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_DisplayBar.SetDisplay'
q['p%24l'] = 'EntrezSystem2'
q['p%24st'] = 'pubmed'
browser.POST('http://www.ncbi.nlm.nih.gov/pubmed', q, {'Accept': 'application/xml'})
xml = between(browser.Page, '<pre>', '</pre>').replace('<', '<').replace('>', '>').strip()
return xml
def External_IP():
r = HttpClient()
r.GET("http://www.wieistmeineip.de/")
ip = between(r.Page, '<strong>', '</strong>')
return ip
def extractTitle(self):
return between(self.page, 'style="color:#000000;">', '<').strip().replace('\n', ' ')