Develop Reference

CSV file being exported empty and only the headers are showing?

So Im learning more about python everyday. Im doing a mini web scrape project and at the very end when I should see the results on an exported csv - it comes up blank except for the headers. Any help is gladly appreciated! Thanks.
The code is below:
import csv
import requests
from bs4 import BeautifulSoup
url = "https://www.boxofficemojo.com/year/"
response = requests.get(url)
html = response.content
soup = BeautifulSoup(html, "html.parser")
box_office_table = soup.find("div", class_="a-section mojo-body aok-relative").find_all("tr")
with open('imdbmovies.csv', 'a', newline='') as csvfile:
writer = csv.writer(csvfile)
# Write headers to CSV file
writer.writerow(['numone_release', 'year', 'total_gross', 'releases', 'average', 'gross_change'])
for row in box_office_table:
try:
year_cell = row.find("td", class_="a-text-left mojo-header-column mojo-field-type-year mojo-sort-column")
money_cells = row.find_all("td", class_="a-text-right mojo-field-type-money")
releases_cell = row.find("td", class_="a-text-right mojo-field-type-positive_integer")
gross_change_cell = row.find("td", class_="a-text-right mojo-number-delta mojo-field-type-percent_delta")
numone_release_cell = row.find("td", class_="a-text-left mojo-field-type-release mojo-cell-wide")
if len(money_cells) >= 2 and year_cell is not None and releases_cell is not None and gross_change_cell is not None and numone_release_cell is not None:
total_gross_cell = money_cells[0]
average_cell = money_cells[1]
year = year_cell.text.strip()
total_gross = total_gross_cell.text.strip()
releases = releases_cell.text.strip()
average = average_cell.text.strip()
gross_change = gross_change_cell.text.strip()
numone_release = numone_release_cell.text.strip()
print(year, total_gross, releases, average, gross_change, numone_release)
# Write the row to the CSV file
writer.writerow([numone_release, year, total_gross, releases, average, gross_change])
except AttributeError:
# Either a cell is not found
pass

Handling HTML in python

I had a problem when I took out html files and imported them into excel.
This is the site i need to get information: https://www.kylc.com/stats/global/yearly_per_country/g_gdp/vnm.html
As you can see, in the GDP table I have a row named : 年份 separated from 2 lines
That's why after i exported the excel file it gave unexpected results
The result I want is that the first line in excel will only have : 年份 , GDP(美元), 占世界%
Sorry for my confusing explanation, I really don't know how to explain it in detail.
Here is my python code
import requests
from bs4 import BeautifulSoup
import lxml
import csv
def get_html(url):
try:
r = requests.get(url)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
r = "fail"
return r
def getGDP(ulist,html):
soup = BeautifulSoup(html,"html.parser")
trs = soup.find_all('tr')
for tr in trs:
list = []
for th in tr:
ts = th.string
if ts == '\n':
continue
list.append(ts)
ulist.append(list)
def saveGDP(ulist):
file_name = '21095010 胡碧玉 GDP.csv'
with open(file_name,'w',errors='ignore',newline='') as f:
f_csv = csv.writer(f)
f_csv.writerows(ulist)
def main():
unifo=[]
url='https://www.kylc.com/stats/global/yearly_per_country/g_gdp/vnm.html'
html=get_html(url)
getGDP(unifo,html)
saveGDP(unifo)
if __name__=="__main__":
main()
Thank you so much!

Using pandas scraping tables and cleaning of results in most cases is mutch easier - under the hood beautifulsoup is working for you.
In this case read_html() the table, drop the unwanted header level and filter out the rows containings ads:
import pandas as pd
df = pd.read_html('https://www.kylc.com/stats/global/yearly_per_country/g_gdp/vnm.html')[0].droplevel(0, axis=1)
df[~df.iloc[:,0].str.contains('ads')].to_csv('21095010 胡碧玉 GDP.csv', index=False)
Answering your question
You have to select your elements more specific e.g. with css selectors.
So first get the thead information from all th witout colspan, than collect the data from all tr in tbody that do not contains ads:
def getGDP(html):
soup = BeautifulSoup(html,"html.parser")
data = []
data.append([th.text for th in soup.select('thead th:not([colspan])')])
for row in soup.select('tbody tr:not(:-soup-contains("ads"))'):
data.append(list(row.stripped_strings))
return data
Example
import requests
from bs4 import BeautifulSoup
import lxml
import csv
def get_html(url):
try:
r = requests.get(url)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
r = "fail"
return r
def getGDP(html):
soup = BeautifulSoup(html,"html.parser")
data = []
data.append([th.text for th in soup.select('thead th:not([colspan])')])
for x in soup.select('tbody tr:not(:-soup-contains("ads"))'):
data.append(list(x.stripped_strings))
return data
def saveGDP(ulist):
file_name = '21095010 胡碧玉 GDP.csv'
print(ulist)
with open(file_name,'w',errors='ignore', encoding='utf-8') as f:
f_csv = csv.writer(f)
f_csv.writerows(ulist)
def main():
url='https://www.kylc.com/stats/global/yearly_per_country/g_gdp/vnm.html'
html=get_html(url)
saveGDP(getGDP(html))
if __name__=="__main__":
main()

I'm trying to deduplicate weblinks scraped using Python & BeautifulSoup but it's not working

I'm trying to scrape a website in Python, I got the links to print but in trying to make them a set to deduplicate, there are still duplicates. Anyone have any advice on what I am doing wrong? Thanks in advance!
Edit: So I tried what John suggested but my csv output is a cascading list of links across the excel sheet, it's crazy...I'll post the changes below this original code:
import requests
from bs4 import BeautifulSoup
page = "https://www.census.gov/programs-surveys/popest.html"
r = requests.get(page)
raw_html = r.text
soup = BeautifulSoup(raw_html, 'html.parser')
mylink = soup.find_all('a')
print ('The number of links to start with are: ', len(mylink) )
#output = The number of links to start with are: 254
import csv
with open('census_links.csv', 'w', newline='') as f:
weblinks = str(mylink)
writer = csv.writer(f, delimiter = ' ', lineterminator = '\r')
for link in mylink:
hrefs = str(link.get('href'))
if hrefs.startswith("None"):
''
elif hrefs.startswith('http'):
MySet = set()
MySet.add(hrefs)
elif hrefs.startswith('#'):
''
elif hrefs.startswith(' '):
''
print(set(MySet))
file.write(str(MySet)+'\n')
file.close
#Edited code:
import requests
from bs4 import BeautifulSoup
page = "https://www.census.gov/programs-surveys/popest.html"
r = requests.get(page)
raw_html = r.text
soup = BeautifulSoup(raw_html, 'html.parser')
mylink = soup.find_all('a')
print ('The number of links to start with are: ', len(mylink))
# The number of links to start with are: 254
import csv
with open('census_links.csv', 'w', newline='') as f:
weblinks = str(mylink)
writer = csv.writer(f, delimiter = ',', lineterminator = '\r')
MySet = set()
for link in mylink:
hrefs = str(link.get('href'))
if hrefs.startswith("None"):
continue
elif hrefs.startswith('#'):
continue
elif hrefs.startswith(' '):
continue
elif hrefs.startswith('http'):
MySet.add(hrefs)
file.write(str(MySet)+'\n')
file.close
print(str(MySet) +'\n')

to get unique links, you want to check if the link is in MySet with hrefs not in MySet.
for simple operation you don't need csv, to write in single row
"\n".join(MySet)
and to write single column
",".join(MySet)
MySet = set()
for link in mylink:
hrefs = link.get('href')
if not hrefs or hrefs.startswith('#'):
continue
# normalize link
if hrefs.startswith('/'):
hrefs = 'https://www.census.gov' + hrefs
# check if link already in MySet
if hrefs not in MySet:
MySet.add(hrefs)
with open('census_links.csv', 'w', newline='') as f:
f.write("\n".join(MySet))
print("\n".join(MySet))

Initialize the set before the loop, and wait to print it until after the loop is done.
MySet = set()
...
for link in mylink:
hrefs = str(link.get('href'))
...
if hrefs.startswith('http'):
MySet.add(hrefs)
...
print(MySet)

same code part to get content.
import requests
from bs4 import BeautifulSoup
page = "https://www.census.gov/programs-surveys/popest.html"
r = requests.get(page)
raw_html = r.text
soup = BeautifulSoup(raw_html, 'html.parser')
mylink = soup.find_all('a')
print ('The number of links to start with are: ', len(mylink) )
#output = The number of links to start with are: 254
use pandas to get the unique url which starts with http.
import pandas as pd
obj = pd.Series(mylink)
obj_link = obj.map(lambda x: x.get('href')).drop_duplicates().dropna()
cond = obj_link.str.startswith('http')
dfn = obj_link.loc[cond].to_frame()
dfn.shape # (93, 1)
dfn.to_csv('census_links.csv', index=False, header=False)

CSV -(excel)- Python. Seems like wrong writing on csv from python

I´m trying to export some data from a website and I first tried on one single page. I´ve to import text delimited by titles:
['Drug name','General Information','Clinical Results','Side Effects','Mechanism of Action','Literature
References','Additional Information','Approval Date','Date Created','Company Name']
The url is https://www.centerwatch.com/directories/1067-fda-approved-drugs/listing/3092-afinitor-everolimus
The code currently works, it gives me all the data. But when I insert it on the CSV , the information is not delimited as I wish.
As it is one single page, the excel should have ONE row... but it doesn´t
The code:
from bs4 import BeautifulSoup
import requests
import csv
csv_file = open('Drugs.csv','w')
csv_writer = csv.writer(csv_file, delimiter ='+')
csv_writer.writerow(['Drug name','General Information','Clinical Results','Side Effects','Mechanism of Action','Literature References','Additional Information','Approval Date','Date Created','Company Name'])
link = requests.get('https://www.centerwatch.com/directories/1067-fda-approved-drugs/listing/3092-afinitor-everolimus')
aux =[]
soup = BeautifulSoup(link.content, 'lxml')
drugName = soup.find('div', class_='company-navigation').find('h1').text
gralInfo = soup.find('div', class_='body directory-listing-profile__description')
y = 0
for h2 in gralInfo.find_all('h2'):
print (y)
text =''
for sibling in h2.find_next_siblings():
if (sibling.name == 'h2'):
break
else:
text = text + sibling.get_text(separator ='\n') + '\n'
print(text)
aux.append(text)
print()
print()
y = y + 1
auxi = []
for info in soup.find_all('div', class_='contact directory-listing-profile__master-detail'):
print(info.text)
auxi.append(info.text)
csv_writer.writerow([drugName, aux[0], aux[1], aux[2], aux[3], aux[4], aux[5], auxi[0], auxi[1], auxi[2]])

Creating a text-delimited file from HTML tables using BeautifulSoup

I'm trying to create a text-delimited file containing the data from the "Actions" table on webpages like this one: http://stats.swehockey.se/Game/Events/300978
I would like each line to include the game # (from the end of the URL) and then the text from the line on the table. For example:
300972 | 60:00 | GK Out | OHK | 33. Hudacek, Julius
I haven't been able to get each row to actually separate. I've tried parsing through each row and column, using a list of stripped strings, and searching by different tags, classes, and styles.
Here's what I currently have:
from bs4 import BeautifulSoup
import urllib.request
def createtext():
gamestr = urlstr + "|"
#Find all table lines. Create one pipe-delimited line for each.
aptext = gamestr
for el in soup.find_all('tr'):
playrow = el.find_all('td', 'tdOdd')
for td in playrow:
if(td.find(text=True)) not in ("", None, "\n"):
aptext = aptext + ''.join(td.text) + "|"
aptext = aptext + "\n" + gamestr
#Creates file with Game # as filename and writes the data to the file
currentfile = urlstr + ".txt"
with open(currentfile, "w") as f:
f.write(str(aptext))
#Grabs the HTML file and creates the soup
urlno = 300978
urlstr = str(urlno)
url = ("http://stats.swehockey.se/Game/Events/" + urlstr)
request = urllib.request.Request(url)
response = urllib.request.urlopen(request)
pbpdoc = response.read().decode('utf-8')
soup = BeautifulSoup(pbpdoc)
createtext()
Thanks for any help or guidance!

First of all, you don't have to construct the CSV data manually, Python provides a built-in csv module for that.
Then, since you are up to "actions" only, I'd identify the "actions" table and find the events-only rows. This can be done with the help of a filtering function checking the first cell to not be empty:
import csv
from bs4 import BeautifulSoup
import requests
def only_action_rows(tag):
if tag.name == 'tr':
first_cell = tag.find('td', class_='tdOdd')
return first_cell and first_cell.get_text(strip=True)
event_id = 300978
url = "http://stats.swehockey.se/Game/Events/{event_id}".format(event_id=event_id)
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
actions_table = soup.find("h2", text="Actions").find_parent("table")
data = [[event_id] + [td.get_text(strip=True) for td in row.find_all('td', class_='tdOdd')]
for row in actions_table.find_all(only_action_rows)]
with open("output.csv", "w") as f:
writer = csv.writer(f)
writer.writerows(data)
Note that I'm using requests here.