コード例 #1
0
    def setSchoolDetails(self):

       for schoolID in self.schoolIDs:

            url = "http://www.education.gov.uk/schools/performance/school/{}".format(schoolID)

            content = getPage(url)
            soup = BeautifulSoup(content)

            queries = ["Head","Street","Town","Postcode","Telephone number"]

            try:
                name = getName(soup)
                attrObject = getItems(soup,queries)
                date,grade,link = getOfsted(soup)
            except PageError:
                continue

            school = SchoolObject(schoolID)
            school.url = url
            school.setName(name)
            school.setAttr(attrObject)
            school.setOfsted(date,grade,link)

            self.schools.append(school)
コード例 #2
0
ファイル: OfstedSearch.py プロジェクト: miskinh/ofsted-scrape
    def getOfstead(self):
        
        url = self.school.report
        content = getPage(url)
        soup = BeautifulSoup(content)
        div = soup.find(class_="download-report-link")

        if not div:
            print("Error for school {}".format(self.school))
            return

        link = div.find("a")
        urlPath = link["href"]
        urlBase = "http://reports.ofsted.gov.uk"

        url = urlBase + urlPath
        report = getPDF(url)
        savePDF(self.filename(),report)
コード例 #3
0
    def searchSchools(self):
        """Searches for schools using the configuration given previously
        the school IDs are stored as a class varaibles for later use
        """

        urlBase = "http://schoolsfinder.direct.gov.uk"
        urlPath = "/school-location-search-results-json/&"

        params = (
            ("searchString", self.postcode),
            ("distanceValue", self.distance)
            )

        urlParams = urllib.parse.urlencode(params)
        url = urlBase+urlPath+urlParams

        pageContent = getPage(url)
        self.setSchools(pageContent)
コード例 #4
0
    def getOfstead(self):

        url = self.school.report
        content = getPage(url)
        soup = BeautifulSoup(content)
        div = soup.find(class_="download-report-link")

        if not div:
            print("Error for school {}".format(self.school))
            return

        link = div.find("a")
        urlPath = link["href"]
        urlBase = "http://reports.ofsted.gov.uk"

        url = urlBase + urlPath
        report = getPDF(url)
        savePDF(self.filename(), report)
コード例 #5
0
    def searchSchools(self):
        """Searches for schools using the configuration given previously
        the school IDs are stored as a class varaibles for later use
        """

        urlBase = "http://www.education.gov.uk"
        urlPath = "/cgi-bin/schools/performance/search.pl?"

        params = (
            ("searchType", "postcode"),
            ("postcode", self.postcode),
            ("distance", self.distance),
            ("phase", "all")
            )

        urlParams = urllib.parse.urlencode(params)
        url = urlBase+urlPath+urlParams

        pageContent = getPage(url)
        self.setSchools(pageContent)